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

llama : add support for Deepseek-R1-Qwen distill model (#11310)

Browse source 
* llama : add support for Deepseek-R1-Qwen distill model

* coding style
This commit is contained in:
Xuan Son Nguyen 2025-01-20 14:35:07 +01:00 • committed by GitHub
parent ef6dada60c
commit ec7f3ac9ab
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 208 additions and 45 deletions
Download patch file Download diff file Expand all files Collapse all files

3
convert_hf_to_gguf.py
View file

@ -696,6 +696,9 @@ class Model:
if chkhsh == "877081d19cf6996e2c4ff0e1236341e9b7bde288f5311a56a937f0afbbb3aeb5":
# ref: https://huggingface.co/deepseek-ai/DeepSeek-V3
res = "deepseek-v3"
if chkhsh == "b3f499bb4255f8ca19fccd664443283318f2fd2414d5e0b040fbdd0cc195d6c5":
# ref: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
res = "deepseek-r1-qwen"
if res is None:
logger.warning("\n")