Skip to content

Can't run codellama #2829

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
guranu opened this issue Aug 27, 2023 · 15 comments
Closed

Can't run codellama #2829

guranu opened this issue Aug 27, 2023 · 15 comments

Comments

@guranu
Copy link

guranu commented Aug 27, 2023

Hello, i downloaded codellama from TheBloke and i compiled llama.cpp with OpenBlas and CLBlast but i get an error when i try to launch it. I am using the latest of the code as the last commit was an hour ago:

~/llama.cpp $ ./main -t 8 -ngl 32 -m models/codellama-7b.Q5_K_S.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -i -ins
main: build = 1085 (1591e2e)
main: seed  = 1693134117
ggml_opencl: selecting platform: 'QUALCOMM Snapdragon(TM)'
ggml_opencl: selecting device: 'QUALCOMM Adreno(TM)'
ggml_opencl: device FP16 support: true
llama_model_loader: loaded meta data with 17 key-value pairs and 291 tensors from models/codellama-7b.Q5_K_S.gguf (version GGUF V1 (latest))
llama_model_loader: - tensor    0:                token_embd.weight q4_0     [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    1:               output_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    2:                    output.weight f16      [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    3:              blk.0.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    4:              blk.0.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    5:              blk.0.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    6:         blk.0.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    7:            blk.0.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    8:            blk.0.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    9:              blk.0.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   10:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   11:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   12:              blk.1.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   13:              blk.1.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   14:              blk.1.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   15:         blk.1.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   16:            blk.1.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   17:            blk.1.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   18:              blk.1.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   19:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   20:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   21:              blk.2.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   22:              blk.2.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   23:              blk.2.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   24:         blk.2.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   25:            blk.2.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   26:            blk.2.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   27:              blk.2.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   28:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   29:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   30:              blk.3.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   31:              blk.3.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   32:              blk.3.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   33:         blk.3.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   34:            blk.3.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   35:            blk.3.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   36:              blk.3.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   37:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   38:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   39:              blk.4.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   40:              blk.4.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   41:              blk.4.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   42:         blk.4.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   43:            blk.4.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   44:            blk.4.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   45:              blk.4.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   46:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   47:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   48:              blk.5.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   49:              blk.5.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   50:              blk.5.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   51:         blk.5.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   52:            blk.5.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   53:            blk.5.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   54:              blk.5.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   55:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   56:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   57:              blk.6.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   58:              blk.6.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   59:              blk.6.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   60:         blk.6.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   61:            blk.6.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   62:            blk.6.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   63:              blk.6.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   64:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   65:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   66:              blk.7.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   67:              blk.7.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   68:              blk.7.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   69:         blk.7.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   70:            blk.7.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   71:            blk.7.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   72:              blk.7.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   73:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   74:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   75:              blk.8.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   76:              blk.8.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   77:              blk.8.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   78:         blk.8.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   79:            blk.8.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   80:            blk.8.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   81:              blk.8.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   82:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   83:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   84:              blk.9.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   85:              blk.9.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   86:              blk.9.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   87:         blk.9.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   88:            blk.9.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   89:            blk.9.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   90:              blk.9.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   91:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   92:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   93:             blk.10.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   94:             blk.10.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   95:             blk.10.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   96:        blk.10.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   97:           blk.10.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   98:           blk.10.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   99:             blk.10.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  100:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  101:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  102:             blk.11.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  103:             blk.11.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  104:             blk.11.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  105:        blk.11.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  106:           blk.11.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  107:           blk.11.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  108:             blk.11.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  109:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  110:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  111:             blk.12.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  112:             blk.12.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  113:             blk.12.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  114:        blk.12.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  115:           blk.12.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  116:           blk.12.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  117:             blk.12.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  118:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  119:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  120:             blk.13.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  121:             blk.13.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  122:             blk.13.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  123:        blk.13.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  124:           blk.13.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  125:           blk.13.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  126:             blk.13.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  127:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  128:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  129:             blk.14.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  130:             blk.14.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  131:             blk.14.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  132:        blk.14.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  133:           blk.14.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  134:           blk.14.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  135:             blk.14.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  136:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  137:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  138:             blk.15.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  139:             blk.15.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  140:             blk.15.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  141:        blk.15.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  143:           blk.15.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  144:             blk.15.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  145:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  146:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  147:             blk.16.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  148:             blk.16.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  149:             blk.16.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  150:        blk.16.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  151:           blk.16.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  152:           blk.16.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  153:             blk.16.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  154:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  155:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  156:             blk.17.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  157:             blk.17.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  158:             blk.17.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  159:        blk.17.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  160:           blk.17.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  161:           blk.17.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  162:             blk.17.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  163:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  164:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  165:             blk.18.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  166:             blk.18.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  167:             blk.18.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  168:        blk.18.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  169:           blk.18.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  170:           blk.18.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  171:             blk.18.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  172:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  173:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  174:             blk.19.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  175:             blk.19.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  176:             blk.19.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  177:        blk.19.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  178:           blk.19.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  179:           blk.19.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  180:             blk.19.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  181:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  182:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  183:             blk.20.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  184:             blk.20.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  185:             blk.20.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  186:        blk.20.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  187:           blk.20.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  188:           blk.20.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  189:             blk.20.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  190:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  191:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  192:             blk.21.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  193:             blk.21.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  194:             blk.21.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  195:        blk.21.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  196:           blk.21.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  197:           blk.21.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  198:             blk.21.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  199:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  200:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  201:             blk.22.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  202:             blk.22.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  203:             blk.22.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  204:        blk.22.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  205:           blk.22.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  206:           blk.22.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  207:             blk.22.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  208:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  209:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  210:             blk.23.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  211:             blk.23.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  212:             blk.23.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  213:        blk.23.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  214:           blk.23.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]     llama_model_loader: - tensor  215:           blk.23.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  216:             blk.23.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]     llama_model_loader: - tensor  217:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  218:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  219:             blk.24.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  220:             blk.24.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  221:             blk.24.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  222:        blk.24.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  223:           blk.24.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  224:           blk.24.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  225:             blk.24.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  226:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  227:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  228:             blk.25.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  229:             blk.25.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  230:             blk.25.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  231:        blk.25.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  232:           blk.25.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  233:           blk.25.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  234:             blk.25.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  235:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  236:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  237:             blk.26.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  238:             blk.26.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  239:             blk.26.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  240:        blk.26.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  241:           blk.26.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  242:           blk.26.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  243:             blk.26.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  244:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  245:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  246:             blk.27.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  247:             blk.27.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  248:             blk.27.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  249:        blk.27.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  250:           blk.27.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  251:           blk.27.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  252:             blk.27.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  253:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  254:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  255:             blk.28.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  256:             blk.28.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  257:             blk.28.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  258:        blk.28.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  259:           blk.28.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  260:           blk.28.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  261:             blk.28.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  262:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  263:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]     llama_model_loader: - tensor  264:             blk.29.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  265:             blk.29.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  266:             blk.29.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  267:        blk.29.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  268:           blk.29.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]     llama_model_loader: - tensor  269:           blk.29.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  270:             blk.29.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]     llama_model_loader: - tensor  271:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  272:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  274:             blk.30.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  275:             blk.30.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  276:        blk.30.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  277:           blk.30.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  278:           blk.30.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  279:             blk.30.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  280:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]     llama_model_loader: - tensor  281:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  282:             blk.31.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  283:             blk.31.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  284:             blk.31.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  285:        blk.31.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  286:           blk.31.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]     llama_model_loader: - tensor  287:           blk.31.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  288:             blk.31.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  289:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]     llama_model_loader: - tensor  290:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str
llama_model_loader: - kv   1:                               general.name str
llama_model_loader: - kv   2:                       llama.context_length u32
llama_model_loader: - kv   3:                     llama.embedding_length u32
llama_model_loader: - kv   4:                          llama.block_count u32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32                                    llama_model_loader: - kv   6:                 llama.rope.dimension_count u32
llama_model_loader: - kv   7:                 llama.attention.head_count u32                                    llama_model_loader: - kv   8:              llama.attention.head_count_kv u32
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32                                    llama_model_loader: - kv  10:                       llama.rope.freq_base f32
llama_model_loader: - kv  11:                          general.file_type u32                                    llama_model_loader: - kv  12:                       tokenizer.ggml.model str
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr                                    llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr                                    llama_model_loader: - kv  16:               general.quantization_version u32
llama_model_loader: - type  f32:   65 tensors           llama_model_loader: - type  f16:    1 tensors
llama_model_loader: - type q4_0:    1 tensors
llama_model_loader: - type q5_K:  224 tensors
llm_load_print_meta: format         = GGUF V1 (latest)  llm_load_print_meta: arch           = llama
llm_load_print_meta: vocab type     = SPM
llm_load_print_meta: n_vocab        = 32016             llm_load_print_meta: n_merges       = 0
llm_load_print_meta: n_ctx_train    = 16384
llm_load_print_meta: n_ctx          = 2048
llm_load_print_meta: n_embd         = 4096              llm_load_print_meta: n_head         = 32                llm_load_print_meta: n_head_kv      = 32
llm_load_print_meta: n_layer        = 32
llm_load_print_meta: n_rot          = 128
llm_load_print_meta: n_gqa          = 1
llm_load_print_meta: f_norm_eps     = 1.0e-05           llm_load_print_meta: f_norm_rms_eps = 1.0e-05           llm_load_print_meta: n_ff           = 11008
llm_load_print_meta: freq_base      = 1000000.0
llm_load_print_meta: freq_scale     = 1
llm_load_print_meta: model type     = 7B                llm_load_print_meta: model ftype    = mostly Q5_K - Small
llm_load_print_meta: model size     = 6.74 B
llm_load_print_meta: general.name   = LLaMA             llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'              llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.09 MB
llm_load_tensors: using OpenCL for GPU acceleration     llm_load_tensors: mem required  =  320.58 MB (+ 1024.00 MB per state)
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloaded 32/33 layers to GPU
llm_load_tensors: VRAM used: 4247 MB                    ...........................................................................................ggml_opencl: (mem = clCreateBuffer(context, CL_MEM_READ_WRITE, size, NULL, &err), err) error -5 at ggml-opencl.cpp:1312
@alonfaraj
Copy link
Contributor

@guranu did you try to lower the number of offloaded gpu layers (-ngl)?
just to check if that's the issue - you can change it to 1.

@guranu
Copy link
Author

guranu commented Aug 27, 2023

@guranu did you try to lower the number of offloaded gpu layers (-ngl)? just to check if that's the issue - you can change it to 1.

Tried that and it worked thanks for the help.

@guranu
Copy link
Author

guranu commented Aug 27, 2023

But now it gives me a "Segmentation fault" error.

@ghost
Copy link

ghost commented Aug 27, 2023 •
edited by ghost
Loading

Hi, it appears you're using an Android with CLBlast, which is okay, except I dunno any Android device that performs better on GPU currently. It's also notable that OpenCL for Android is bugged. It'll run, but I'd use CPU for now.

As for the segmant fault, if I understand correctly then this should've been already resolved, but try adding -p "Hi." to your main, and let me know if the segment fault still occurs.

Edit: Assuming I'm correct about Android then where are you storing your model? Navigate to the model in Termux, type pwd, and show the result please.

@guranu
Copy link
Author

guranu commented Aug 27, 2023 •
edited
Loading

Hi, it appears you're using an Android with CLBlast, which is okay, except I dunno any Android device that performs better on GPU currently. It's also notable that OpenCL for Android is bugged. It'll run, but I'd use CPU for now.

As for the segmant fault, if I understand correctly then this should've been already resolved, but try adding -p "Hi." to your main, and let me know if the segment fault still occurs.

Edit: Assuming I'm correct about Android then where are you storing your model? Navigate to the model in Termux, type pwd, and show the result please.

Well i don't get a segmentation fault error anymore but it dosen't do anything like it dosen't type anything. Oh and the model is stored in /data/data/com.termux/files/home/llama.cpp/models and here are the """results"""":

~/llama.cpp $ ./main -t 8 -ngl 16 -m models/codellama-7b.Q5_K_S.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Write a python code that converts a png to a jpg."
main: build = 1085 (1591e2e)
main: seed  = 1693151191
ggml_opencl: selecting platform: 'QUALCOMM Snapdragon(TM)'
ggml_opencl: selecting device: 'QUALCOMM Adreno(TM)'
ggml_opencl: device FP16 support: true
llama_model_loader: loaded meta data with 17 key-value pairs and 291 tensors from models/codellama-7b.Q5_K_S.gguf (version GGUF V1 (latest))
llama_model_loader: - tensor    0:                token_embd.weight q4_0     [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    1:               output_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    2:                    output.weight f16      [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    3:              blk.0.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    4:              blk.0.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    5:              blk.0.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    6:         blk.0.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    7:            blk.0.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    8:            blk.0.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    9:              blk.0.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   10:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   11:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   12:              blk.1.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   13:              blk.1.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   14:              blk.1.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   15:         blk.1.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   16:            blk.1.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   17:            blk.1.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   18:              blk.1.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   19:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   20:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   21:              blk.2.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   22:              blk.2.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   23:              blk.2.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   24:         blk.2.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   25:            blk.2.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   26:            blk.2.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   27:              blk.2.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   28:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   29:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   30:              blk.3.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   31:              blk.3.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   32:              blk.3.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   33:         blk.3.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   34:            blk.3.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   35:            blk.3.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   36:              blk.3.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   37:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   38:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   39:              blk.4.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   40:              blk.4.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   41:              blk.4.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   42:         blk.4.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   43:            blk.4.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   44:            blk.4.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   45:              blk.4.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   46:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   47:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   48:              blk.5.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   49:              blk.5.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   50:              blk.5.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   51:         blk.5.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   52:            blk.5.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   53:            blk.5.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   54:              blk.5.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   55:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   56:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   57:              blk.6.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   58:              blk.6.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   59:              blk.6.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   60:         blk.6.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   61:            blk.6.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   62:            blk.6.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   63:              blk.6.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   64:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   65:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   66:              blk.7.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   67:              blk.7.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   68:              blk.7.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   69:         blk.7.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   70:            blk.7.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   71:            blk.7.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   72:              blk.7.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   73:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   74:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   75:              blk.8.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   76:              blk.8.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   77:              blk.8.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   78:         blk.8.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   79:            blk.8.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   80:            blk.8.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   81:              blk.8.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   82:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   83:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   84:              blk.9.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   85:              blk.9.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   86:              blk.9.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   87:         blk.9.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   88:            blk.9.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   89:            blk.9.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   90:              blk.9.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   91:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   92:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   93:             blk.10.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   94:             blk.10.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   95:             blk.10.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   96:        blk.10.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   97:           blk.10.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   98:           blk.10.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   99:             blk.10.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  100:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  101:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  102:             blk.11.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  103:             blk.11.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  104:             blk.11.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  105:        blk.11.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  106:           blk.11.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  107:           blk.11.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  108:             blk.11.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  109:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  110:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  111:             blk.12.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  112:             blk.12.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  113:             blk.12.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  114:        blk.12.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  115:           blk.12.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  116:           blk.12.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  117:             blk.12.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  118:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  119:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  120:             blk.13.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  121:             blk.13.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  122:             blk.13.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  123:        blk.13.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  124:           blk.13.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  125:           blk.13.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  126:             blk.13.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  127:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  128:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  129:             blk.14.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  130:             blk.14.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  131:             blk.14.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  132:        blk.14.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  133:           blk.14.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  134:           blk.14.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  135:             blk.14.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  136:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  137:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  138:             blk.15.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  139:             blk.15.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  140:             blk.15.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  141:        blk.15.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  143:           blk.15.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  144:             blk.15.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  145:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  146:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  147:             blk.16.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  148:             blk.16.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  149:             blk.16.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  150:        blk.16.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  151:           blk.16.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  152:           blk.16.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  153:             blk.16.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  154:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  155:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  156:             blk.17.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  157:             blk.17.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  158:             blk.17.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  159:        blk.17.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  160:           blk.17.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  161:           blk.17.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  162:             blk.17.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  163:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  164:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  165:             blk.18.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  166:             blk.18.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  167:             blk.18.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  168:        blk.18.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  169:           blk.18.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  170:           blk.18.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  171:             blk.18.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  172:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  173:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  174:             blk.19.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  175:             blk.19.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  176:             blk.19.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  177:        blk.19.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  178:           blk.19.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  179:           blk.19.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  180:             blk.19.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  181:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  182:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  183:             blk.20.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  184:             blk.20.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  185:             blk.20.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  186:        blk.20.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  187:           blk.20.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  188:           blk.20.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  189:             blk.20.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  190:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  191:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  192:             blk.21.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  193:             blk.21.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  194:             blk.21.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  195:        blk.21.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  196:           blk.21.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  197:           blk.21.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  198:             blk.21.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  199:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  200:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  201:             blk.22.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  202:             blk.22.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  203:             blk.22.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  204:        blk.22.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  205:           blk.22.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  206:           blk.22.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  207:             blk.22.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  208:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  209:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  210:             blk.23.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  211:             blk.23.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  212:             blk.23.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  213:        blk.23.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  214:           blk.23.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  215:           blk.23.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  216:             blk.23.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  217:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  218:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  219:             blk.24.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  220:             blk.24.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  221:             blk.24.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  222:        blk.24.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  223:           blk.24.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  224:           blk.24.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  225:             blk.24.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  226:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  227:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  228:             blk.25.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  229:             blk.25.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  230:             blk.25.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  231:        blk.25.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  232:           blk.25.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  233:           blk.25.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  234:             blk.25.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  235:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  236:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  237:             blk.26.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  238:             blk.26.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  239:             blk.26.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  240:        blk.26.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  241:           blk.26.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  242:           blk.26.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  243:             blk.26.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  244:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  245:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  246:             blk.27.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  247:             blk.27.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  248:             blk.27.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  249:        blk.27.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  250:           blk.27.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  251:           blk.27.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  252:             blk.27.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  253:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  254:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  255:             blk.28.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  256:             blk.28.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  257:             blk.28.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  258:        blk.28.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  259:           blk.28.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  260:           blk.28.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  261:             blk.28.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  262:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  263:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  264:             blk.29.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  265:             blk.29.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  266:             blk.29.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  267:        blk.29.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  268:           blk.29.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  269:           blk.29.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  270:             blk.29.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  271:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  272:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  274:             blk.30.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  275:             blk.30.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  276:        blk.30.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  277:           blk.30.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  278:           blk.30.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  279:             blk.30.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  280:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  281:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  282:             blk.31.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  283:             blk.31.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  284:             blk.31.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  285:        blk.31.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  286:           blk.31.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  287:           blk.31.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  288:             blk.31.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  289:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  290:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str
llama_model_loader: - kv   1:                               general.name str
llama_model_loader: - kv   2:                       llama.context_length u32
llama_model_loader: - kv   3:                     llama.embedding_length u32
llama_model_loader: - kv   4:                          llama.block_count u32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32
llama_model_loader: - kv   7:                 llama.attention.head_count u32
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32
llama_model_loader: - kv  10:                       llama.rope.freq_base f32
llama_model_loader: - kv  11:                          general.file_type u32
llama_model_loader: - kv  12:                       tokenizer.ggml.model str
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr
llama_model_loader: - kv  16:               general.quantization_version u32
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type  f16:    1 tensors
llama_model_loader: - type q4_0:    1 tensors
llama_model_loader: - type q5_K:  224 tensors
llm_load_print_meta: format         = GGUF V1 (latest)
llm_load_print_meta: arch           = llama
llm_load_print_meta: vocab type     = SPM
llm_load_print_meta: n_vocab        = 32016
llm_load_print_meta: n_merges       = 0
llm_load_print_meta: n_ctx_train    = 16384
llm_load_print_meta: n_ctx          = 2048
llm_load_print_meta: n_embd         = 4096
llm_load_print_meta: n_head         = 32
llm_load_print_meta: n_head_kv      = 32
llm_load_print_meta: n_layer        = 32
llm_load_print_meta: n_rot          = 128
llm_load_print_meta: n_gqa          = 1
llm_load_print_meta: f_norm_eps     = 1.0e-05
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: n_ff           = 11008
llm_load_print_meta: freq_base      = 1000000.0
llm_load_print_meta: freq_scale     = 1
llm_load_print_meta: model type     = 7B
llm_load_print_meta: model ftype    = mostly Q5_K - Small
llm_load_print_meta: model size     = 6.74 B
llm_load_print_meta: general.name   = LLaMA
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.09 MB
llm_load_tensors: using OpenCL for GPU acceleration
llm_load_tensors: mem required  = 2444.08 MB (+ 1024.00 MB per state)
llm_load_tensors: offloading 16 repeating layers to GPU
llm_load_tensors: offloaded 16/33 layers to GPU
llm_load_tensors: VRAM used: 2124 MB
...............................................................................................
llama_new_context_with_model: kv self size  = 1024.00 MB
llama_new_context_with_model: compute buffer total size =  153.41 MB

system_info: n_threads = 8 / 8 | AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 |
sampling: repeat_last_n = 64, repeat_penalty = 1.100000, presence_penalty = 0.000000, frequency_penalty = 0.000000, top_k = 40, tfs_z = 1.000000, top_p = 0.950000, typical_p = 1.000000, temp = 0.700000, mirostat = 0, mirostat_lr = 0.100000, mirostat_ent = 5.000000
generate: n_ctx = 2048, n_batch = 512, n_predict = -1, n_keep = 0


 Write a python code that converts a png to a jpg.

it did absoluteley nothing.

@ghost
Copy link

ghost commented Aug 27, 2023

@klosax if I correctly understand then he shouldn't have to add a prompt, but getting seg fault even though this was resolved with https://github.com/ggerganov/llama.cpp/releases/tag/b1046. Adding -p "Hi." fixed the error.

@guranu Your model location is good. You may be over-loading your device with -t 8 which would look like llama.cpp doing nothing. Trying lowering threads, I dunno what device you're using, but for me -t 3is ideal.

@guranu
Copy link
Author

guranu commented Aug 27, 2023

@klosax if I correctly understand then he shouldn't have to add a prompt, but getting seg fault even though this was resolved with https://github.com/ggerganov/llama.cpp/releases/tag/b1046. Adding -p "Hi." fixed the error.

@guranu Your model location is good. You may be over-loading your device with -t 8 which would look like llama.cpp doing nothing. Trying lowering threads, I dunno what device you're using, but for me -t 3is ideal.

Nope that didn't help at all. Also my device is a Oneplus 7.

@guranu
Copy link
Author

guranu commented Aug 27, 2023

well it dosen't do nothing now i does "something" it says that it uses 0.48 tokens per second but i didn't get any kind of text:

llama_print_timings:        load time = 11207.86 ms
llama_print_timings:      sample time =   109.30 ms /    46 runs   (    2.38 ms per token,   420.84 tokens per second)
llama_print_timings: prompt eval time = 75283.40 ms /    36 tokens ( 2091.21 ms per token,     0.48 tokens per second)
llama_print_timings:        eval time = 191829.02 ms /    46 runs   ( 4170.20 ms per token,     0.24 tokens per second)
llama_print_timings:       total time = 315230.57 ms

@ghost
Copy link

ghost commented Aug 27, 2023

it says that it uses 0.48 tokens per second but i didn't get any kind of text:

The device is over-loaded, so try 4_K_M or 4_K_S as Q5_K_S is quite large. gsmarena shows that device has 8 cores, but you may need to find the best --threads # for it.

I'd lower -ngl to 0, or 1 until the best --threads for your device is identified.

@guranu
Copy link
Author

guranu commented Aug 28, 2023

After setting the thread count to 2 i managed to get some kind of text however the text is stupid:

~/llama.cpp $ ./main -t 2 -ngl 1 -m models/codellama-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -i -ins                                       main: build = 1085 (1591e2e)
main: seed  = 1693234323                                ggml_opencl: selecting platform: 'QUALCOMM Snapdragon(TM)'                                                      ggml_opencl: selecting device: 'QUALCOMM Adreno(TM)'
ggml_opencl: device FP16 support: true                  llama_model_loader: loaded meta data with 17 key-value pairs and 291 tensors from models/codellama-7b.Q4_K_M.gguf (version GGUF V1 (latest))
llama_model_loader: - tensor    0:                token_embd.weight q4_0     [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    1:               output_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    2:                    output.weight f16      [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    3:              blk.0.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    4:              blk.0.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    5:              blk.0.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    6:         blk.0.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    7:            blk.0.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    8:            blk.0.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    9:              blk.0.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   10:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   11:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   12:              blk.1.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   13:              blk.1.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   14:              blk.1.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   15:         blk.1.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   16:            blk.1.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   17:            blk.1.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   18:              blk.1.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   19:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   20:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   21:              blk.2.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   22:              blk.2.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   23:              blk.2.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   24:         blk.2.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   25:            blk.2.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   26:            blk.2.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   27:              blk.2.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   28:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   29:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   30:              blk.3.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   31:              blk.3.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   32:              blk.3.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   33:         blk.3.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   34:            blk.3.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   35:            blk.3.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   36:              blk.3.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   37:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   38:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   39:              blk.4.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   40:              blk.4.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   41:              blk.4.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   42:         blk.4.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   43:            blk.4.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   44:            blk.4.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   45:              blk.4.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   46:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   47:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   48:              blk.5.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   49:              blk.5.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   50:              blk.5.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   51:         blk.5.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   52:            blk.5.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   53:            blk.5.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   54:              blk.5.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   55:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   56:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   57:              blk.6.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   58:              blk.6.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   59:              blk.6.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   60:         blk.6.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   61:            blk.6.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   62:            blk.6.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   63:              blk.6.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   64:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   65:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   66:              blk.7.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   67:              blk.7.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   68:              blk.7.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   69:         blk.7.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   70:            blk.7.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   71:            blk.7.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   72:              blk.7.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   73:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   74:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   75:              blk.8.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   76:              blk.8.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   77:              blk.8.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   78:         blk.8.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   79:            blk.8.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   80:            blk.8.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   81:              blk.8.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   82:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   83:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   84:              blk.9.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   85:              blk.9.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   86:              blk.9.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   87:         blk.9.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   88:            blk.9.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   89:            blk.9.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   90:              blk.9.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   91:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   92:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   93:             blk.10.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   94:             blk.10.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   95:             blk.10.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   96:        blk.10.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   97:           blk.10.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   98:           blk.10.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   99:             blk.10.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  100:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  101:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  102:             blk.11.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  103:             blk.11.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  104:             blk.11.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  105:        blk.11.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  106:           blk.11.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  107:           blk.11.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  108:             blk.11.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  109:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  110:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  111:             blk.12.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  112:             blk.12.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  113:             blk.12.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  114:        blk.12.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  115:           blk.12.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  116:           blk.12.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  117:             blk.12.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  118:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  119:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  120:             blk.13.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  121:             blk.13.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  122:             blk.13.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  123:        blk.13.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  124:           blk.13.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  125:           blk.13.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  126:             blk.13.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  127:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  128:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  129:             blk.14.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  130:             blk.14.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  131:             blk.14.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  132:        blk.14.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  133:           blk.14.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  134:           blk.14.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  135:             blk.14.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  136:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  137:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  138:             blk.15.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  139:             blk.15.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  140:             blk.15.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  141:        blk.15.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  143:           blk.15.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  144:             blk.15.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  145:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  146:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  147:             blk.16.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  148:             blk.16.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  149:             blk.16.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  150:        blk.16.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  151:           blk.16.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  152:           blk.16.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  153:             blk.16.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  154:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  155:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  156:             blk.17.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  157:             blk.17.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  158:             blk.17.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  159:        blk.17.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  160:           blk.17.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  161:           blk.17.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  162:             blk.17.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  163:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  164:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  165:             blk.18.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  166:             blk.18.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  167:             blk.18.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  168:        blk.18.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  169:           blk.18.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  170:           blk.18.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  171:             blk.18.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  172:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  173:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  174:             blk.19.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  175:             blk.19.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  176:             blk.19.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  177:        blk.19.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  178:           blk.19.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  179:           blk.19.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  180:             blk.19.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  181:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  182:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  183:             blk.20.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  184:             blk.20.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  185:             blk.20.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  186:        blk.20.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  187:           blk.20.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  188:           blk.20.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  189:             blk.20.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  190:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  191:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  192:             blk.21.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  193:             blk.21.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  194:             blk.21.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  195:        blk.21.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  196:           blk.21.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  197:           blk.21.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  198:             blk.21.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  199:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  200:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  201:             blk.22.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  202:             blk.22.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  203:             blk.22.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  204:        blk.22.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  205:           blk.22.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  206:           blk.22.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  207:             blk.22.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  208:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  209:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  210:             blk.23.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  211:             blk.23.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  212:             blk.23.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  213:        blk.23.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  214:           blk.23.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  215:           blk.23.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  216:             blk.23.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  217:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  218:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  219:             blk.24.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  220:             blk.24.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  221:             blk.24.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  222:        blk.24.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  223:           blk.24.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  224:           blk.24.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  225:             blk.24.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  226:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  227:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  228:             blk.25.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  229:             blk.25.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  230:             blk.25.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  231:        blk.25.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  232:           blk.25.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  233:           blk.25.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  234:             blk.25.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  235:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  236:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  237:             blk.26.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  238:             blk.26.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  239:             blk.26.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  240:        blk.26.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  241:           blk.26.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  242:           blk.26.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  243:             blk.26.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  244:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  245:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  246:             blk.27.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  247:             blk.27.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  248:             blk.27.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  249:        blk.27.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  250:           blk.27.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  251:           blk.27.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  252:             blk.27.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  253:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  254:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  255:             blk.28.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  256:             blk.28.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  257:             blk.28.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  258:        blk.28.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  259:           blk.28.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  260:           blk.28.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  261:             blk.28.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  262:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]     llama_model_loader: - tensor  263:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  264:             blk.29.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  265:             blk.29.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  266:             blk.29.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  267:        blk.29.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  268:           blk.29.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  269:           blk.29.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]     llama_model_loader: - tensor  270:             blk.29.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]     llama_model_loader: - tensor  271:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  272:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  274:             blk.30.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  275:             blk.30.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  276:        blk.30.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  277:           blk.30.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  278:           blk.30.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]     llama_model_loader: - tensor  279:             blk.30.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  280:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  281:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]     llama_model_loader: - tensor  282:             blk.31.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  283:             blk.31.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  284:             blk.31.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]     llama_model_loader: - tensor  285:        blk.31.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  286:           blk.31.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]     llama_model_loader: - tensor  287:           blk.31.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  288:             blk.31.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  289:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  290:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str                                    llama_model_loader: - kv   1:                               general.name str                                    llama_model_loader: - kv   2:                       llama.context_length u32                                    llama_model_loader: - kv   3:                     llama.embedding_length u32                                    llama_model_loader: - kv   4:                          llama.block_count u32                                    llama_model_loader: - kv   5:                  llama.feed_forward_length u32                                    llama_model_loader: - kv   6:                 llama.rope.dimension_count u32                                    llama_model_loader: - kv   7:                 llama.attention.head_count u32                                    llama_model_loader: - kv   8:              llama.attention.head_count_kv u32                                    llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32                                    llama_model_loader: - kv  10:                       llama.rope.freq_base f32                                    llama_model_loader: - kv  11:                          general.file_type u32                                    llama_model_loader: - kv  12:                       tokenizer.ggml.model str                                    llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr                                    llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr                                    llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr                                    llama_model_loader: - kv  16:               general.quantization_version u32                                    llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type  f16:    1 tensors           llama_model_loader: - type q4_0:    1 tensors
llama_model_loader: - type q4_K:  192 tensors           llama_model_loader: - type q6_K:   32 tensors
llm_load_print_meta: format         = GGUF V1 (latest)  llm_load_print_meta: arch           = llama
llm_load_print_meta: vocab type     = SPM               llm_load_print_meta: n_vocab        = 32016
llm_load_print_meta: n_merges       = 0                 llm_load_print_meta: n_ctx_train    = 16384
llm_load_print_meta: n_ctx          = 2048              llm_load_print_meta: n_embd         = 4096
llm_load_print_meta: n_head         = 32                llm_load_print_meta: n_head_kv      = 32
llm_load_print_meta: n_layer        = 32                llm_load_print_meta: n_rot          = 128
llm_load_print_meta: n_gqa          = 1                 llm_load_print_meta: f_norm_eps     = 1.0e-05
llm_load_print_meta: f_norm_rms_eps = 1.0e-05           llm_load_print_meta: n_ff           = 11008
llm_load_print_meta: freq_base      = 1000000.0         llm_load_print_meta: freq_scale     = 1
llm_load_print_meta: model type     = 7B                llm_load_print_meta: model ftype    = mostly Q4_K - Medium                                                      llm_load_print_meta: model size     = 6.74 B
llm_load_print_meta: general.name   = LLaMA             llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'               llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'            llm_load_tensors: ggml ctx size =    0.09 MB
llm_load_tensors: using OpenCL for GPU acceleration     llm_load_tensors: mem required  = 3915.15 MB (+ 1024.00 MB per state)                                           llm_load_tensors: offloading 1 repeating layers to GPU
llm_load_tensors: offloaded 1/33 layers to GPU          llm_load_tensors: VRAM used: 124 MB
...............................................................................................
llama_new_context_with_model: kv self size  = 1024.00 MBllama_new_context_with_model: compute buffer total size =  153.41 MB                                            
system_info: n_threads = 2 / 8 | AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 |
main: interactive mode on.                              Reverse prompt: '### Instruction:
                                                        '
sampling: repeat_last_n = 64, repeat_penalty = 1.100000, presence_penalty = 0.000000, frequency_penalty = 0.000000, top_k = 40, tfs_z = 1.000000, top_p = 0.950000, typical_p = 1.000000, temp = 0.700000, mirostat = 0, mirostat_lr = 0.100000, mirostat_ent = 5.000000                generate: n_ctx = 2048, n_batch = 512, n_predict = -1, n_keep = 2                                               
                                                        == Running in interactive mode. ==
 - Press Ctrl+C to interject at any time.                - Press Return to return control to LLaMa.
 - To return control without starting a new line, end your input with '/'.
 - If you want to submit another line, end your input with '\'.
                                                        
> write a python script that converts a png to dds      uh short bro moment
u r full/pad/pad                                        >
                                                        llama_print_timings:        load time =  3521.63 ms
llama_print_timings:      sample time =    25.72 ms /    12 runs   (    2.14 ms per token,   466.56 tokens per second)                                                  llama_print_timings: prompt eval time = 22526.53 ms /    33 tokens (  682.62 ms per token,     1.46 tokens per second)
llama_print_timings:        eval time = 89659.79 ms /    12 runs   ( 7471.65 ms per token,     0.13 tokens per second)                                                  llama_print_timings:       total time = 208723.94 ms

@grahameth grahameth mentioned this issue Aug 28, 2023
Merged
@ghost
Copy link

ghost commented Aug 28, 2023

At least llama.cpp is working now. Theres 2 reasons for bad quality in your run:

  1. GPU is bugged, so the text produced by Android GPU is currently unreliable - it's a known issue. Try building llama.cpp on CPU. Here's instructions to build for CPU

  2. Codellama behaves like an auto-complete. Try changing your prompt to something like this: -p "Here's a Python script that converts a PNG to DDS: "

I find the instruct model slightly easier to use, but it's personal taste. Here's a prompt template for Codellama Instruct: -p "<s>[INST] create a short sample JSON for an A.I. character named Bob.[/INST]"

@guranu
Copy link
Author

guranu commented Aug 28, 2023

It seemed to be working "fine" on the cpu though for some reason i had to type the prompt twice:

~/llama.cpp $ ./main -t 4 -m models/codellama-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -i -ins
main: build = 1085 (1591e2e)
main: seed  = 1693241134
llama_model_loader: loaded meta data with 17 key-value pairs and 291 tensors from models/codellama-7b.Q4_K_M.gguf (version GGUF V1 (latest))
llama_model_loader: - tensor    0:                token_embd.weight q4_0     [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    1:               output_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    2:                    output.weight f16      [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    3:              blk.0.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    4:              blk.0.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    5:              blk.0.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    6:         blk.0.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    7:            blk.0.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    8:            blk.0.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    9:              blk.0.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   10:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   11:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   12:              blk.1.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   13:              blk.1.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   14:              blk.1.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   15:         blk.1.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   16:            blk.1.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   17:            blk.1.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   18:              blk.1.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   19:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   20:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   21:              blk.2.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   22:              blk.2.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   23:              blk.2.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   24:         blk.2.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   25:            blk.2.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   26:            blk.2.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   27:              blk.2.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   28:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   29:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   30:              blk.3.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   31:              blk.3.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   32:              blk.3.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   33:         blk.3.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   34:            blk.3.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   35:            blk.3.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   36:              blk.3.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   37:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   38:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   39:              blk.4.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   40:              blk.4.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   41:              blk.4.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   42:         blk.4.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   43:            blk.4.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   44:            blk.4.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   45:              blk.4.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   46:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   47:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   48:              blk.5.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   49:              blk.5.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   50:              blk.5.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   51:         blk.5.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   52:            blk.5.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   53:            blk.5.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   54:              blk.5.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   55:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   56:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   57:              blk.6.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   58:              blk.6.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   59:              blk.6.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   60:         blk.6.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   61:            blk.6.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   62:            blk.6.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   63:              blk.6.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   64:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   65:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   66:              blk.7.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   67:              blk.7.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   68:              blk.7.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   69:         blk.7.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   70:            blk.7.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   71:            blk.7.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   72:              blk.7.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   73:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   74:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   75:              blk.8.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   76:              blk.8.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   77:              blk.8.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   78:         blk.8.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   79:            blk.8.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   80:            blk.8.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   81:              blk.8.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   82:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   83:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   84:              blk.9.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   85:              blk.9.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   86:              blk.9.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   87:         blk.9.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   88:            blk.9.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   89:            blk.9.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   90:              blk.9.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   91:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   92:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   93:             blk.10.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   94:             blk.10.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   95:             blk.10.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   96:        blk.10.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   97:           blk.10.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   98:           blk.10.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   99:             blk.10.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  100:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  101:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  102:             blk.11.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  103:             blk.11.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  104:             blk.11.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  105:        blk.11.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  106:           blk.11.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  107:           blk.11.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  108:             blk.11.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  109:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  110:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  111:             blk.12.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  112:             blk.12.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  113:             blk.12.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  114:        blk.12.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  115:           blk.12.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  116:           blk.12.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  117:             blk.12.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  118:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  119:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  120:             blk.13.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  121:             blk.13.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  122:             blk.13.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  123:        blk.13.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  124:           blk.13.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  125:           blk.13.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  126:             blk.13.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  127:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  128:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  129:             blk.14.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  130:             blk.14.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  131:             blk.14.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  132:        blk.14.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  133:           blk.14.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  134:           blk.14.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  135:             blk.14.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  136:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  137:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  138:             blk.15.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  139:             blk.15.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  140:             blk.15.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  141:        blk.15.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  143:           blk.15.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  144:             blk.15.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  145:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  146:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  147:             blk.16.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  148:             blk.16.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  149:             blk.16.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  150:        blk.16.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  151:           blk.16.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  152:           blk.16.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  153:             blk.16.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  154:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  155:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  156:             blk.17.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  157:             blk.17.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  158:             blk.17.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  159:        blk.17.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  160:           blk.17.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  161:           blk.17.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  162:             blk.17.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  163:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  164:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  165:             blk.18.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  166:             blk.18.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  167:             blk.18.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  168:        blk.18.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  169:           blk.18.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  170:           blk.18.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  171:             blk.18.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  172:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  173:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  174:             blk.19.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  175:             blk.19.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  176:             blk.19.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  177:        blk.19.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  178:           blk.19.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  179:           blk.19.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  180:             blk.19.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  181:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  182:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  183:             blk.20.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  184:             blk.20.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  185:             blk.20.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  186:        blk.20.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  187:           blk.20.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  188:           blk.20.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  189:             blk.20.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  190:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  191:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  192:             blk.21.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  193:             blk.21.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  194:             blk.21.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  195:        blk.21.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  196:           blk.21.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  197:           blk.21.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  198:             blk.21.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  199:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  200:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  201:             blk.22.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  202:             blk.22.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  203:             blk.22.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  204:        blk.22.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  205:           blk.22.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  206:           blk.22.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  207:             blk.22.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  208:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  209:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  210:             blk.23.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  211:             blk.23.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  212:             blk.23.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  213:        blk.23.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  214:           blk.23.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  215:           blk.23.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  216:             blk.23.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  217:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  218:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  219:             blk.24.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  220:             blk.24.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  221:             blk.24.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  222:        blk.24.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  223:           blk.24.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  224:           blk.24.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  225:             blk.24.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  226:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  227:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  228:             blk.25.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  229:             blk.25.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  230:             blk.25.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  231:        blk.25.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  232:           blk.25.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  233:           blk.25.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  234:             blk.25.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  235:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  236:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  237:             blk.26.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  238:             blk.26.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  239:             blk.26.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  240:        blk.26.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  241:           blk.26.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  242:           blk.26.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  243:             blk.26.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  244:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  245:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  246:             blk.27.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  247:             blk.27.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  248:             blk.27.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  249:        blk.27.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  250:           blk.27.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  251:           blk.27.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  252:             blk.27.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  253:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  254:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  255:             blk.28.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  256:             blk.28.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  257:             blk.28.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  258:        blk.28.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  259:           blk.28.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  260:           blk.28.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  261:             blk.28.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  262:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  263:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  264:             blk.29.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  265:             blk.29.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  266:             blk.29.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  267:        blk.29.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  268:           blk.29.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  269:           blk.29.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  270:             blk.29.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  271:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  272:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  274:             blk.30.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  275:             blk.30.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  276:        blk.30.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  277:           blk.30.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  278:           blk.30.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  279:             blk.30.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  280:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  281:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  282:             blk.31.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  283:             blk.31.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  284:             blk.31.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  285:        blk.31.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  286:           blk.31.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  287:           blk.31.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  288:             blk.31.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  289:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  290:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str
llama_model_loader: - kv   1:                               general.name str
llama_model_loader: - kv   2:                       llama.context_length u32
llama_model_loader: - kv   3:                     llama.embedding_length u32
llama_model_loader: - kv   4:                          llama.block_count u32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32
llama_model_loader: - kv   7:                 llama.attention.head_count u32
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32
llama_model_loader: - kv  10:                       llama.rope.freq_base f32
llama_model_loader: - kv  11:                          general.file_type u32
llama_model_loader: - kv  12:                       tokenizer.ggml.model str
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr
llama_model_loader: - kv  16:               general.quantization_version u32
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type  f16:    1 tensors
llama_model_loader: - type q4_0:    1 tensors
llama_model_loader: - type q4_K:  192 tensors
llama_model_loader: - type q6_K:   32 tensors
llm_load_print_meta: format         = GGUF V1 (latest)
llm_load_print_meta: arch           = llama
llm_load_print_meta: vocab type     = SPM
llm_load_print_meta: n_vocab        = 32016
llm_load_print_meta: n_merges       = 0
llm_load_print_meta: n_ctx_train    = 16384
llm_load_print_meta: n_ctx          = 2048
llm_load_print_meta: n_embd         = 4096
llm_load_print_meta: n_head         = 32
llm_load_print_meta: n_head_kv      = 32
llm_load_print_meta: n_layer        = 32
llm_load_print_meta: n_rot          = 128
llm_load_print_meta: n_gqa          = 1
llm_load_print_meta: f_norm_eps     = 1.0e-05
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: n_ff           = 11008
llm_load_print_meta: freq_base      = 1000000.0
llm_load_print_meta: freq_scale     = 1
llm_load_print_meta: model type     = 7B
llm_load_print_meta: model ftype    = mostly Q4_K - Medium
llm_load_print_meta: model size     = 6.74 B
llm_load_print_meta: general.name   = LLaMA
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.09 MB
llm_load_tensors: mem required  = 4038.95 MB (+ 1024.00 MB per state)
...............................................................................................
llama_new_context_with_model: kv self size  = 1024.00 MB
llama_new_context_with_model: compute buffer total size =  153.41 MB

system_info: n_threads = 4 / 8 | AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 |
main: interactive mode on.
Reverse prompt: '### Instruction:

'
sampling: repeat_last_n = 64, repeat_penalty = 1.100000, presence_penalty = 0.000000, frequency_penalty = 0.000000, top_k = 40, tfs_z = 1.000000, top_p = 0.950000, typical_p = 1.000000, temp = 0.700000, mirostat = 0, mirostat_lr = 0.100000, mirostat_ent = 5.000000
generate: n_ctx = 2048, n_batch = 512, n_predict = -1, n_keep = 2


== Running in interactive mode. ==
 - Press Ctrl+C to interject at any time.
 - Press Return to return control to LLaMa.
 - To return control without starting a new line, end your input with '/'.
 - If you want to submit another line, end your input with '\'.


> write a python code that converts a png to dds

write a python code that converts a png to dds

import bpy, os, sys
import json
from bpy_extras.image_io import dds_pack
sys.path.append(os.getcwd())

def save_dds(context):
    scene = context.scene

    # get current file path
    path = bpy.data.filepath

    # add an image to the file path
    filename, ext = os.path.splitext(bpy.data.filepath)
    new_filename = filename + "dds"
    png_file = filename + ".png"
    png_image = bpy.data.images[os.path.basename(png_file)]

    dds_pack.export_to_dds_file(scene, png_image, new_filename)

llama_print_timings: load time = 7100.79 ms
llama_print_timings: sample time = 346.68 ms / 194 runs ( 1.79 ms per token, 559.60 tokens per second)
llama_print_timings: prompt eval time = 30452.95 ms / 61 tokens ( 499.23 ms per token, 2.00 tokens per second)
llama_print_timings: eval time = 1100701.07 ms / 193 runs ( 5703.11 ms per token, 0.18 tokens per second)
llama_print_timings: total time = 1249614.05 ms

@ghost
Copy link

ghost commented Aug 28, 2023 •
edited by ghost
Loading

-ins is instruct mode, which may be difficult for a model that's not instructIon-based to adhere to. Either use an instruct model, or try without -ins

To improve the responsiveness slightly, try adding -b 10 to your prompt as it'll respond a little faster with a lower batch #. Here's more performance tips from the README.

Looks resolved.

@guranu
Copy link
Author

guranu commented Aug 30, 2023

-ins is instruct mode, which may be difficult for a model that's not instructIon-based to adhere to. Either use an instruct model, or try without -ins

To improve the responsiveness slightly, try adding -b 10 to your prompt as it'll respond a little faster with a lower batch #. Here's more performance tips from the README.

Looks resolved.

Not yet, when added -b 10 the performance improved but now it's halucinating:

~/llama.cpp $ ./main -t 4 -m models/codellama-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -b 10 -n -1 -i -ins
main: build = 1085 (1591e2e)
main: seed  = 1693401436
llama_model_loader: loaded meta data with 17 key-value pairs and 291 tensors from models/codellama-7b.Q4_K_M.gguf (version GGUF V1 (latest))
llama_model_loader: - tensor    0:                token_embd.weight q4_0     [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    1:               output_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    2:                    output.weight f16      [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    3:              blk.0.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    4:              blk.0.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    5:              blk.0.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    6:         blk.0.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    7:            blk.0.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    8:            blk.0.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    9:              blk.0.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   10:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   11:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   12:              blk.1.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   13:              blk.1.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   14:              blk.1.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   15:         blk.1.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   16:            blk.1.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   17:            blk.1.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   18:              blk.1.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   19:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   20:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   21:              blk.2.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   22:              blk.2.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   23:              blk.2.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   24:         blk.2.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   25:            blk.2.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   26:            blk.2.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   27:              blk.2.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   28:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   29:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   30:              blk.3.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   31:              blk.3.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   32:              blk.3.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   33:         blk.3.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   34:            blk.3.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   35:            blk.3.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   36:              blk.3.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   37:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   38:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   39:              blk.4.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   40:              blk.4.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   41:              blk.4.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   42:         blk.4.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   43:            blk.4.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   44:            blk.4.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   45:              blk.4.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   46:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   47:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   48:              blk.5.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   49:              blk.5.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   50:              blk.5.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   51:         blk.5.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   52:            blk.5.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   53:            blk.5.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   54:              blk.5.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   55:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   56:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   57:              blk.6.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   58:              blk.6.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   59:              blk.6.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   60:         blk.6.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   61:            blk.6.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   62:            blk.6.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   63:              blk.6.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   64:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   65:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   66:              blk.7.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   67:              blk.7.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   68:              blk.7.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   69:         blk.7.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   70:            blk.7.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   71:            blk.7.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   72:              blk.7.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   73:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   74:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   75:              blk.8.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   76:              blk.8.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   77:              blk.8.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   78:         blk.8.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   79:            blk.8.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   80:            blk.8.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   81:              blk.8.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   82:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   83:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   84:              blk.9.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   85:              blk.9.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   86:              blk.9.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   87:         blk.9.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   88:            blk.9.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   89:            blk.9.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   90:              blk.9.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   91:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   92:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   93:             blk.10.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   94:             blk.10.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   95:             blk.10.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   96:        blk.10.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   97:           blk.10.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   98:           blk.10.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   99:             blk.10.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  100:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  101:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  102:             blk.11.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  103:             blk.11.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  104:             blk.11.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  105:        blk.11.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  106:           blk.11.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  107:           blk.11.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  108:             blk.11.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  109:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  110:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  111:             blk.12.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  112:             blk.12.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  113:             blk.12.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  114:        blk.12.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  115:           blk.12.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  116:           blk.12.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  117:             blk.12.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  118:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  119:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  120:             blk.13.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  121:             blk.13.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  122:             blk.13.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  123:        blk.13.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  124:           blk.13.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  125:           blk.13.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  126:             blk.13.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  127:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  128:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  129:             blk.14.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  130:             blk.14.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  131:             blk.14.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  132:        blk.14.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  133:           blk.14.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  134:           blk.14.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  135:             blk.14.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  136:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  137:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  138:             blk.15.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  139:             blk.15.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  140:             blk.15.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  141:        blk.15.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  143:           blk.15.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  144:             blk.15.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  145:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  146:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  147:             blk.16.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  148:             blk.16.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  149:             blk.16.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  150:        blk.16.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  151:           blk.16.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  152:           blk.16.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  153:             blk.16.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  154:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  155:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  156:             blk.17.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  157:             blk.17.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  158:             blk.17.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  159:        blk.17.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  160:           blk.17.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  161:           blk.17.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  162:             blk.17.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  163:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  164:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  165:             blk.18.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  166:             blk.18.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  167:             blk.18.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  168:        blk.18.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  169:           blk.18.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  170:           blk.18.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  171:             blk.18.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  172:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  173:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  174:             blk.19.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  175:             blk.19.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  176:             blk.19.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  177:        blk.19.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  178:           blk.19.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  179:           blk.19.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  180:             blk.19.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  181:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  182:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  183:             blk.20.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  184:             blk.20.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  185:             blk.20.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  186:        blk.20.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  187:           blk.20.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  188:           blk.20.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  189:             blk.20.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  190:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  191:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  192:             blk.21.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  193:             blk.21.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  194:             blk.21.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  195:        blk.21.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  196:           blk.21.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  197:           blk.21.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  198:             blk.21.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  199:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  200:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  201:             blk.22.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  202:             blk.22.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  203:             blk.22.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  204:        blk.22.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  205:           blk.22.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  206:           blk.22.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  207:             blk.22.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  208:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  209:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  210:             blk.23.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  211:             blk.23.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  212:             blk.23.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  213:        blk.23.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  214:           blk.23.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  215:           blk.23.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  216:             blk.23.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  217:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  218:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  219:             blk.24.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  220:             blk.24.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  221:             blk.24.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  222:        blk.24.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  223:           blk.24.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  224:           blk.24.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  225:             blk.24.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  226:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  227:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  228:             blk.25.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  229:             blk.25.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  230:             blk.25.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  231:        blk.25.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  232:           blk.25.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  233:           blk.25.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  234:             blk.25.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  235:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  236:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  237:             blk.26.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  238:             blk.26.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  239:             blk.26.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  240:        blk.26.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  241:           blk.26.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  242:           blk.26.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  243:             blk.26.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  244:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  245:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  246:             blk.27.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  247:             blk.27.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  248:             blk.27.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  249:        blk.27.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  250:           blk.27.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  251:           blk.27.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  252:             blk.27.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  253:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  254:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  255:             blk.28.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  256:             blk.28.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  257:             blk.28.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  258:        blk.28.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  259:           blk.28.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  260:           blk.28.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  261:             blk.28.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  262:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  263:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  264:             blk.29.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  265:             blk.29.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  266:             blk.29.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  267:        blk.29.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  268:           blk.29.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  269:           blk.29.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  270:             blk.29.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  271:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  272:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  274:             blk.30.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  275:             blk.30.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  276:        blk.30.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  277:           blk.30.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  278:           blk.30.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  279:             blk.30.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  280:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  281:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  282:             blk.31.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  283:             blk.31.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  284:             blk.31.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  285:        blk.31.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  286:           blk.31.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  287:           blk.31.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  288:             blk.31.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  289:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  290:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str
llama_model_loader: - kv   1:                               general.name str
llama_model_loader: - kv   2:                       llama.context_length u32
llama_model_loader: - kv   3:                     llama.embedding_length u32
llama_model_loader: - kv   4:                          llama.block_count u32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32
llama_model_loader: - kv   7:                 llama.attention.head_count u32
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32
llama_model_loader: - kv  10:                       llama.rope.freq_base f32
llama_model_loader: - kv  11:                          general.file_type u32
llama_model_loader: - kv  12:                       tokenizer.ggml.model str
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr
llama_model_loader: - kv  16:               general.quantization_version u32
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type  f16:    1 tensors
llama_model_loader: - type q4_0:    1 tensors
llama_model_loader: - type q4_K:  192 tensors
llama_model_loader: - type q6_K:   32 tensors
llm_load_print_meta: format         = GGUF V1 (latest)
llm_load_print_meta: arch           = llama
llm_load_print_meta: vocab type     = SPM
llm_load_print_meta: n_vocab        = 32016
llm_load_print_meta: n_merges       = 0
llm_load_print_meta: n_ctx_train    = 16384
llm_load_print_meta: n_ctx          = 2048
llm_load_print_meta: n_embd         = 4096
llm_load_print_meta: n_head         = 32
llm_load_print_meta: n_head_kv      = 32
llm_load_print_meta: n_layer        = 32
llm_load_print_meta: n_rot          = 128
llm_load_print_meta: n_gqa          = 1
llm_load_print_meta: f_norm_eps     = 1.0e-05
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: n_ff           = 11008
llm_load_print_meta: freq_base      = 1000000.0
llm_load_print_meta: freq_scale     = 1
llm_load_print_meta: model type     = 7B
llm_load_print_meta: model ftype    = mostly Q4_K - Medium
llm_load_print_meta: model size     = 6.74 B
llm_load_print_meta: general.name   = LLaMA
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.09 MB
llm_load_tensors: mem required  = 4038.95 MB (+ 1024.00 MB per state)
...............................................................................................
llama_new_context_with_model: kv self size  = 1024.00 MB
llama_new_context_with_model: compute buffer total size =    4.38 MB

system_info: n_threads = 4 / 8 | AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 |
main: interactive mode on.
Reverse prompt: '### Instruction:

'
sampling: repeat_last_n = 64, repeat_penalty = 1.100000, presence_penalty = 0.000000, frequency_penalty = 0.000000, top_k = 40, tfs_z = 1.000000, top_p = 0.950000, typical_p = 1.000000, temp = 0.700000, mirostat = 0, mirostat_lr = 0.100000, mirostat_ent = 5.000000
generate: n_ctx = 2048, n_batch = 10, n_predict = -1, n_keep = 2


== Running in interactive mode. ==
 - Press Ctrl+C to interject at any time.
 - Press Return to return control to LLaMa.
 - To return control without starting a new line, end your input with '/'.
 - If you want to submit another line, end your input with '\'.


> write a code that converts a png to dds
* You should be able to run the program using `python3 convert_png2dds.py [--force] <path/to/image.png>`
  * `--force` overwrites existing files without asking
* A file with `.dds` extension will be created in the same directory as the input png file, and if you use `--force`, it will replace an existing file of the same name
* If you try to convert a file that doesn't have a `.png` extension, or can't be found, it will print an error message. You should also see something like `WARNING: failed to load image from 'path/to/image.png'` in your console output (or stderr)
* If the conversion is successful, you should see `SUCCESS: converted <path/to/image.dds>` or `SUCCESS: converted <path/to/image.png> -> <path/to/image.dds>` if `--force` was used
  * It may be worth noting that the
> write a python code that converts a png to dds
* You should be able to run the program using `python3 convert_png2dds.py [--force] <path/to/image.png>`
  * `--force` overwrites existing files without asking
* A file with `.dds` extension will be created in the same directory as the input png file, and if you use `--force`, it will replace an existing file of the same name
* If you try to convert a file that doesn't have a `.png` extension, or can't be found, it will print an error message. You should also see something like `WARNING: failed to load image from 'path/to/image.png'` in your console output (or stderr)
* If the conversion is successful, you should see `SUCCESS: converted <path/to/image.dds>` or `SUCCESS: converted <path/to/image.png> -> <path/to/image.dds>` if `--force` was used
  * It may be worth noting that the

> huh?? i don't have the python script that your talking about.
#### 1)
```shell
sudo git clone https://github.com/Kiraboi907/kiddo-protector.git

then cd kiddo-protector then run it with ./main.py

or

2)

Download this .zip file. Then extract the file and cd into the folder you extracted then run it with ./main.py

If you don't know how to download, cd or any other terminal command, please see this link. Then if you don't know what an .zip file is, see this link.

3)

You can find the main.py file in kiddo-protector/bin. You can also run it with python main.py or ./main.py if you're on a UNIX based system. It should be executable and runnable by double clicking if you're using Windows.

the github link is dead.
I'm sorry I can't find the repo again. But if you have any further questions, you can feel free to contact me through my email: [email protected]

llama_print_timings: load time = 7159.67 ms
llama_print_timings: sample time = 1254.70 ms / 777 runs ( 1.61 ms per token, 619.27 tokens per second)
llama_print_timings: prompt eval time = 22503.10 ms / 116 tokens ( 193.99 ms per token, 5.15 tokens per second)
llama_print_timings: eval time = 236613.32 ms / 777 runs ( 304.52 ms per token, 3.28 tokens per second)
llama_print_timings: total time = 419883.06

@ghost
Copy link

ghost commented Aug 30, 2023

It's resolved because Codellama/llama.cpp is working, though it's unclear why you're prompting it that way as that was addressed 2 days ago.

@guranu guranu closed this as completed Aug 30, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@alonfaraj @guranu