main.py modified

migrated to groq -- suuuuuper fast!

Delete Phi-3-mini-4k-instruct-q4.gguf

Delete Meta-Llama-3-8B-Instruct-v2.Q4_K_S.gguf

Update Dockerfile

Update Dockerfile

Delete entrypoint.sh

Update Dockerfile

Update README.md

Update Dockerfile

Update README.md

Update README.md

Update Dockerfile

Update Dockerfile

Create entrypoint.sh

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

this will work (fr)

Update main.py

Update Dockerfile

trying things and failing fast

Update requirements.txt

Update main.py

Update Dockerfile

Update .gitignore

Upload Phi-3-mini-4k-instruct-q4.gguf with huggingface_hub

main.py updated

modification to how server is started, calling from uvicorn now instead of going through py

fix for the fix

some modifications, this is hacky. I'm trying to get some tangible result first and then will polish everything for production

a fix which may work

reqs

test-llama3, not sure how it'll go on langserve

gitignore added

[add-model] llama-8b-instruct

dockerfile addition

initial commit