diff options
| author | saood06 <saood05@gmail.com> | 2025-05-09 09:17:41 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-09 09:17:41 -0500 |
| commit | 967a2e1860482397a6a386952d972ac1205474ad (patch) | |
| tree | e5fce0dba400eaf98ba343a06f007ddad408e5ce /src/llama.cpp | |
| parent | e5a4a3ce78ce96b6822dcd6138a98c4d237ecc9b (diff) | |
Fix missing rope_freqs with convert_hf_to_gguf (#402)
* lora : fix llama conversion script with ROPE_FREQS
* convert : refactor rope_freqs generation
This should also fix vocab-only conversion for Phi-3.
* convert : adapt MiniCPM3 to separate rope_freqs insertion
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.
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Francis Couture-Harpin <git@compilade.net>
Diffstat (limited to 'src/llama.cpp')
0 files changed, 0 insertions, 0 deletions