ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : add pre-tokenizer regexes for BLOOM and gpt3-finnish (#8850)

Browse source
This commit is contained in:
Esko Toivonen 2024-08-15 10:17:12 +03:00 • committed by GitHub
parent d5492f0525
commit 6bda7ce6c3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 19 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert_hf_to_gguf_update.py
View file

@ -94,6 +94,8 @@ models = [
{"name": "codeshell", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/WisdomShell/CodeShell-7B", },
{"name": "tekken", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", },
{"name": "smollm", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/HuggingFaceTB/SmolLM-135M", },
{'name': "bloom", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigscience/bloom", },
{'name': "gpt3-finnish", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/TurkuNLP/gpt3-finnish-small", },
]