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

convert : fix gemma v1 tokenizer convert (#8248)

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-07-04 10:41:03 +03:00 • committed by GitHub
parent f619024764
commit 20fc3804bf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 85 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

5
convert-hf-to-gguf-update.py
View file

@ -86,6 +86,8 @@ models = [
{"name": "poro-chat", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LumiOpen/Poro-34B-chat", },
{"name": "jina-v2-code", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-code", },
{"name": "viking", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LumiOpen/Viking-7B", }, # Also used for Viking 13B and 33B
{"name": "gemma", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/google/gemma-2b", },
{"name": "gemma-2", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/google/gemma-2-9b", },
{"name": "jais", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/core42/jais-13b", },
]
@ -273,7 +275,8 @@ tests = [
"3333333",
"33333333",
"333333333",
# "Cửa Việt", # llama-bpe fails on this
"Cửa Việt", # llama-bpe fails on this
" discards",
chktxt,
]