Hugging Face's logo

Spaces:
kairusama
/
gemma-3-4b-it-qat
Running

App Files Community
kairusama commited on
Commit
13ab7a4
·
verified ·
1 Parent(s): 6999f88

switched to google's repo due to mismatch dimension with mmproj (wrong file?)

Browse files
Files changed (1) hide show
  1. Dockerfile +3 -3
Dockerfile CHANGED
@@ -2,7 +2,7 @@ FROM ghcr.io/ggml-org/llama.cpp:full
2
 
3
  RUN apt update && apt install wget -y
4
 
5
- RUN wget "https://huggingface.co/lmstudio-community/gemma-3-1B-it-qat-GGUF/resolve/main/gemma-3-1B-it-QAT-Q4_0.gguf" -O /gemma-3-1B-it-QAT-Q4_0.gguf
6
- RUN wget "https://huggingface.co/lmstudio-community/gemma-3-4B-it-qat-GGUF/resolve/main/mmproj-model-f16.gguf" -O /mmproj-model-f16.gguf
7
 
8
- CMD ["--server", "-m", "/gemma-3-1B-it-QAT-Q4_0.gguf", "--mmproj", "/mmproj-model-f16.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "512"]
 
2
 
3
  RUN apt update && apt install wget -y
4
 
5
+ RUN wget "https://huggingface.co/google/gemma-3-4b-it-qat-q4_0-gguf/resolve/main/gemma-3-4b-it-q4_0.gguf" -O /gemma-3-4b-it-q4_0.gguf
6
+ RUN wget "https://huggingface.co/google/gemma-3-4b-it-qat-q4_0-gguf/resolve/main/mmproj-model-f16-4B.gguf" -O /mmproj-model-f16-4B.gguf
7
 
8
+ CMD ["--server", "-m", "/gemma-3-4b-it-q4_0.gguf", "--mmproj", "/mmproj-model-f16-4B.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "512"]