llama.cpp
b75c3816 - convert : allow conversion of Mistral HF models (#6144)

Commit
1 year ago
convert : allow conversion of Mistral HF models (#6144) * Allow conversion of Mistral HF models * Homogenize Llama, Mistral, Mixtral under the same entry. * Fix tokenizer, permute tensors * Use sentencepiece tokenizer, or fall back to hfft. * convert-hf : small fix for mypy * convert-hf : fix duplicated block_count * convert-hf : add vocab size to metadata --------- Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Author
Parents
Loading