CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : support InfiniAI Megrez 3b (#10893)

Browse Source 
* Support InfiniAI Megrez 3b

* Fix tokenizer_clean_spaces for megrez
This commit is contained in:
Yun Dou
2024-12-23 08:35:44 +08:00
committed by GitHub
parent 6f0c9e034b
commit b92a14a841
4 changed files with 25 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
convert_hf_to_gguf.py
View File

@@ -684,6 +684,9 @@ class Model:
if chkhsh == "ad851be1dba641f2e3711822f816db2c265f788b37c63b4e1aeacb9ee92de8eb":
# ref: https://huggingface.co/ai-sage/GigaChat-20B-A3B-instruct
res = "gigachat"
if chkhsh == "d4c8f286ea6b520b3d495c4455483cfa2302c0cfcd4be05d781b6a8a0a7cdaf1":
# ref: https://huggingface.co/Infinigence/Megrez-3B-Instruct
res = "megrez"
if res is None:
logger.warning("\n")