ggml-org/gguf-my-repo

Fix Git Cloning (#209)

Fix model-id search dropdown overlapping Quantization Method label (#207)

remove extra whitespaces from app.py

Update README.md

hopefully this fixes it (#176)

Update Dockerfile (#175)

Update Dockerfile (#174)

Update Dockerfile (#173)

Add -DLLAMA_CURL=OFF

Fix Gradio Demo (#162)

URGENT: CVE's/vulns Present, Update Dependencies (#155)

Attempt to fix apt install (#154)

add oauth token validation before running

again, fix error message

fix error message for non logged in

show error toast message if user is not logged in

remove -DLLAMA_CURL

Update Dockerfile

Update start.sh

fix error message when user not logged in

Better isolation + various improvements (#133)

fix downloads dir

add docker compose for dev locally (#130)

throw an error if selected model is PEFT (#131)

Download fixes (#127)

change script name convert-hf-to-gguf.py ==> convert_hf_to_gguf.py (#98)

Update app.py (#91)

Update start.sh (#90)

Update app.py (#89)

enable scrolling (#86)

Update app.py (#85)

Update Dockerfile (#82)

Update start.sh (#81)

imatrix support (#80)

Update app.py (#79)

hotfix: model_id (#76)

patch: fix the base_model definition. (#75)

Update the default model created with the space. (#74)

Remove references to convert.py (#73)

Split/shard support (#65)

Split/shard support (#64)

Disable Gradio Telemetry (#39)

Update app.py (#61)

Update Dockerfile (#60)

Add Background Scheduler for daily refresh (#59)

Update app.py (#54)

Update app.py (#53)

Move `LoginButton` outside of Interface block (#52)

Hot fix (#50)

Use OAuth ("Sign in with Hugging Face") (#49)