Update README.md

fix the table

Update app.py

Update app.py

big refactor to include original model card

update names and fix tags

Update README.md

Fix the bug about the GGML version number

Update app.py

DLLAMA_CURL=OFF (#5)

Update Dockerfile

Update app.py

Update README.md

Update README.md

Add the X address and github address to the generated readme file.

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

adjust restart to be 1 day

Roll back Docker and start.sh so that llama.cpp is compiled in start.sh

Fix bugs about showing error picture when processing model.

Change Dockerfile and start.sh to move building llama.cpp to the docker building process. Therefore, we can save time in dev mode to restart the app

Update Dockerfile

Update app.py

Update app.py

Update app.py

Change the dockerfile so that we can run the space in dev mode

Add Error Message for not login, Change the readme format, Change the repo name

Update app.py

Update app.py

Update start.sh

Update Dockerfile

Update app.py

Update app.py

Update start.sh

Update app.py

Save the model to the data directory

add missing env variable

add persistant storage

use persistant storage for some of the library

add cleanup and storage

format

Update app.py

Update Dockerfile

Update app.py (#4)

Upload 10 files (#3)

Update app.py (#2)

Update README.md