Spaces:
Sleeping
Sleeping
Ved Gupta
commited on
Commit
·
c1aa71b
1
Parent(s):
be43a34
Update Dockerfile and README.md
Browse files- Dockerfile +1 -3
- README.md +0 -3
Dockerfile
CHANGED
|
@@ -3,10 +3,8 @@ FROM python:3.9-alpine
|
|
| 3 |
RUN apk add --no-cache build-base cmake git wget gcc g++ make
|
| 4 |
RUN pip install llama-cpp-python sse_starlette starlette_context pydantic_settings fastapi uvicorn
|
| 5 |
|
| 6 |
-
|
| 7 |
RUN mkdir models
|
| 8 |
RUN wget -q "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/mistral-7b-instruct-v0.2.Q4_0.gguf" -O models/mistral-7b-instruct-v0.2.Q4_0.gguf
|
| 9 |
|
| 10 |
-
|
| 11 |
EXPOSE 8080
|
| 12 |
-
CMD ["python", "-m", "llama_cpp.server", "--model", "models/mistral-7b-instruct-v0.2.Q4_0.gguf"]
|
|
|
|
| 3 |
RUN apk add --no-cache build-base cmake git wget gcc g++ make
|
| 4 |
RUN pip install llama-cpp-python sse_starlette starlette_context pydantic_settings fastapi uvicorn
|
| 5 |
|
|
|
|
| 6 |
RUN mkdir models
|
| 7 |
RUN wget -q "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/mistral-7b-instruct-v0.2.Q4_0.gguf" -O models/mistral-7b-instruct-v0.2.Q4_0.gguf
|
| 8 |
|
|
|
|
| 9 |
EXPOSE 8080
|
| 10 |
+
CMD ["python", "-m", "llama_cpp.server", "--model", "models/mistral-7b-instruct-v0.2.Q4_0.gguf", "--host", "0.0.0.0", "--port", "8080"]
|
README.md
CHANGED
|
@@ -10,9 +10,6 @@ app_port: 8080
|
|
| 10 |
|
| 11 |
|
| 12 |
```bash
|
| 13 |
-
CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python
|
| 14 |
-
wget -q "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/mistral-7b-instruct-v0.2.Q4_0.gguf" -O models/mistral-7b-instruct-v0.2.Q4_0.gguf
|
| 15 |
-
|
| 16 |
|
| 17 |
curl https://innovatorved-api.hf.space/v1/models
|
| 18 |
|
|
|
|
| 10 |
|
| 11 |
|
| 12 |
```bash
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
curl https://innovatorved-api.hf.space/v1/models
|
| 15 |
|