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

llama-model : add Glm4Model implementation for GLM-4-0414 (#12867)

Browse source 
* GLM-4-0414

* use original one

* Using with tensor map

* fix bug

* change order

* change order

* format with flask8
This commit is contained in:
Yuxuan Zhang 2025-04-11 18:10:10 +08:00 • committed by GitHub
parent 0c50923944
commit 06bb53ad9b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 273 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

1
convert_hf_to_gguf_update.py
View file

@ -114,6 +114,7 @@ models = [
{"name": "trillion", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/trillionlabs/Trillion-7B-preview", },
{"name": "bailingmoe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/inclusionAI/Ling-lite", },
{"name": "llama4", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct", },
{"name": "glm4", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/THUDM/glm-4-9b-hf", },
]