Fix missing rope_freqs with convert_hf_to_gguf#402
Merged
Conversation
This should also fix vocab-only conversion for Phi-3.
MiniCPM3's tokenizer is treated as a SentencePiece tokenizer to avoid having to run its custom Python code which mixes tokenization in the same file as tool calls. gguf-py : add long and short RoPE factors to tensor mappings Empty, but the key names are used to populate the mappings.
ikawrakow
approved these changes
May 9, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This ports ggml-org/llama.cpp#9396 and ggml-org/llama.cpp#9117 (I don't think I needed this as the changes in here are basically reverted in 9396).
The issue was that the convert script used generate_extra_tensors for those tensors but there was no code that called that function.
I tested with Llama-3_1-Nemotron-51B-Instruct and it now generates the rope_freqs.weight which was missing previously.
Look at #377 for more information.