vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add OLMo to pre-tokenizer generation script

Browse source
This commit is contained in:
nopperl 2024-05-05 20:55:10 +02:00
parent 628b299106
commit c80768392a
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
convert-hf-to-gguf-update.py
View file

@ -67,6 +67,7 @@ models = [
{"name": "gpt-2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/openai-community/gpt2", },
{"name": "refact", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/smallcloudai/Refact-1_6-base", },
{"name": "command-r", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/CohereForAI/c4ai-command-r-v01", },
{"name": "olmo", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/allenai/OLMo-1.7-7B-hf", },
]
# make directory "models/tokenizers" if it doesn't exist