Update Dockerfile

Dockerfile

@@ -26,8 +26,8 @@ ENV PATH="/usr/local/cuda/bin:$PATH" \
 WORKDIR /app
 
 # Download ggml and mmproj models from HuggingFace
-RUN wget https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/ggml-yi-34b-f16-q_5_k.gguf && \
-    wget https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/mmproj-llava-34b-f16-q6_k.gguf
+RUN wget https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/mistral-7b-q_5_k.gguf && \
+    wget https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/mmproj-mistral7b-f16.gguf
 
 # Clone and build llava-server with CUDA support
 RUN ls -al
@@ -37,4 +37,4 @@ RUN make LLAMA_CUBLAS=1
 EXPOSE 8080
 
 # Start the llava-server with models
-CMD ["--server", "--model", "ggml-yi-34b-f16-q_5_k.gguf", "--mmproj", "mmproj-llava-34b-f16-q6_k.gguf", "--threads", "6", "--host", "0.0.0.0", "-ngl", "61"]
+CMD ["--server", "--model", "mistral-7b-q_5_k.gguf", "--mmproj", "mmproj-mistral7b-f16.gguf", "--threads", "6", "--host", "0.0.0.0", "-ngl", "31"]