neph1 commited on
Commit
f125926
·
verified ·
1 Parent(s): 3c12fa9

Update Dockerfile

Browse files
Files changed (1) hide show
  1. Dockerfile +2 -2
Dockerfile CHANGED
@@ -6,7 +6,7 @@ WORKDIR /home/app
6
 
7
  RUN apt update
8
  RUN apt install -y wget make cmake clang git g++
9
- #RUN wget https://huggingface.co/mradermacher/bellman-mistral-7b-instruct-v0.3-GGUF/resolve/main/bellman-mistral-7b-instruct-v0.3.Q5_K_M.gguf?download=true -O model.gguf
10
  RUN git clone https://github.com/ggerganov/llama.cpp
11
  RUN mv llama.cpp llama_temp
12
  RUN mv llama_temp/* .
@@ -18,4 +18,4 @@ RUN chmod +x ./build/bin/llama-server
18
 
19
  EXPOSE 7860
20
 
21
- CMD ["sh", "-c", "./build/bin/llama-server --hf-repo mradermacher/bellman-mistral-7b-instruct-v0.3-GGUF/ --hf-file bellman-mistral-7b-instruct-v0.3.Q5_K_M.gguf -c 4096 --host 0.0.0.0 --port 7860"]
 
6
 
7
  RUN apt update
8
  RUN apt install -y wget make cmake clang git g++
9
+ RUN wget https://huggingface.co/mradermacher/bellman-mistral-7b-instruct-v0.3-GGUF/resolve/main/bellman-mistral-7b-instruct-v0.3.Q5_K_M.gguf?download=true -O model.gguf
10
  RUN git clone https://github.com/ggerganov/llama.cpp
11
  RUN mv llama.cpp llama_temp
12
  RUN mv llama_temp/* .
 
18
 
19
  EXPOSE 7860
20
 
21
+ CMD ["sh", "-c", "./build/bin/llama-server -m /home/app/model.gguf -c 4096 -n 1024 --host 0.0.0.0 --port 7860"]