File size: 687 Bytes
092a975
 
 
 
 
 
 
 
f125926
495083b
 
 
06e89e2
 
a9ce82d
53791da
 
092a975
 
 
a60ec09
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
FROM python:3.12

RUN useradd -m -u 1000 app

WORKDIR /home/app

RUN apt update
RUN apt install -y wget make cmake clang git g++
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
RUN git clone https://github.com/ggerganov/llama.cpp
RUN mv llama.cpp llama_temp
RUN mv llama_temp/* .
RUN cmake -B build
RUN cmake --build build --config Release
#RUN apt install socat -y
#RUN ls -R | grep -i "llama-server"
#RUN chmod +x ./build/bin/llama-server

EXPOSE 7860

CMD ["sh", "-c", "./build/bin/llama-server -m /home/app/model.gguf -c 4096 -n 1024 --host 0.0.0.0 --port 7860"]