error loading model

[milobestcat]

Describe the bug

Hi I tried to follow the manual installation steps but I couldn't get the server run. After some online research, i thought the problem might be due to the pytorch installation, so I tried this to install it: pip install -U --pre torch torchvision -f https://download.pytorch.org/whl/nightly/cpu/torch_nightly.html.
Now the server is able to run as I tested it on some simple LLM models.
Then I tested it on ggml 13b and here is the error:
llama.cpp: loading model from models/eachadea_ggml-vicuna-13b-1.1/ggml-old-vic13b-q4_0.bin
llama_model_load_internal: format = ggjt v1 (pre #1405)
llama_model_load_internal: n_vocab = 32000
llama_model_load_internal: n_ctx = 2048
llama_model_load_internal: n_embd = 5120
llama_model_load_internal: n_mult = 256
llama_model_load_internal: n_head = 40
llama_model_load_internal: n_layer = 40
llama_model_load_internal: n_rot = 128
llama_model_load_internal: ftype = 4 (mostly Q4_1, some F16)
llama_model_load_internal: n_ff = 13824
llama_model_load_internal: n_parts = 1
llama_model_load_internal: model size = 13B
error loading model: this format is no longer supported (see ggml-org/llama.cpp#1305)
llama_init_from_file: failed to load model
Exception ignored in: <function LlamaCppModel.del at 0x13c546200>
Traceback (most recent call last):
File "/Users/yingxiao.kong/text-generation-webui/modules/llamacpp_model.py", line 23, in del
self.model.del()
AttributeError: 'LlamaCppModel' object has no attribute 'model'

Is there an existing issue for this?

• I have searched the existing issues

Reproduction

To reproduce it, follow all the manual installation steps in the instruction but only replace the step for pytorch installation with: pip install -U --pre torch torchvision -f https://download.pytorch.org/whl/nightly/cpu/torch_nightly.html

Screenshot

No response

Logs

llama.cpp: loading model from models/eachadea_ggml-vicuna-13b-1.1/ggml-old-vic13b-q4_0.bin
llama_model_load_internal: format     = ggjt v1 (pre #1405)
llama_model_load_internal: n_vocab    = 32000
llama_model_load_internal: n_ctx      = 2048
llama_model_load_internal: n_embd     = 5120
llama_model_load_internal: n_mult     = 256
llama_model_load_internal: n_head     = 40
llama_model_load_internal: n_layer    = 40
llama_model_load_internal: n_rot      = 128
llama_model_load_internal: ftype      = 4 (mostly Q4_1, some F16)
llama_model_load_internal: n_ff       = 13824
llama_model_load_internal: n_parts    = 1
llama_model_load_internal: model size = 13B
error loading model: this format is no longer supported (see https://github.com/ggerganov/llama.cpp/pull/1305)
llama_init_from_file: failed to load model
Exception ignored in: <function LlamaCppModel.__del__ at 0x13c546200>
Traceback (most recent call last):
  File "/Users/yingxiao.kong/text-generation-webui/modules/llamacpp_model.py", line 23, in __del__
    self.model.__del__()
AttributeError: 'LlamaCppModel' object has no attribute 'model'

System Info

I'm using a mac M1 32GB pro
macOS: 13.3.1

[cnodon]

same issue here

[strnad]

you have old version of ggml model, download new one

error loading model: this format is no longer supported (see ggml-org/llama.cpp#1305)

[valdesguefa]

@strnad which version can we download ?. i a tire to download model and then have the error.

[gandolfi974]

same problem with "WizardLM-13B-Uncensored-GGML"

[YingxiaoKong]

@gandolfi974 @valdesguefa try to download the stable-vicuna-13B.ggml.q5_1.bin