sbdie/QP_AN

pycache files temporary before gitignore

Upload LLamandementFineTuneAvecNotation16Q.gguf with huggingface_hub

renamed: LLamandementFineTuneAvecNotation16Q.gguf -> models/LLamandementFineTuneAvecNotation16Q.gguf

Upload LLamandementFineTuneAvecNotation16Q.gguf with huggingface_hub

restablish server.py

change 2 server.py

change server.py

gitaddtestsbdietonoquest

remove temoin3

removed gitaddtest

gitaddtest

Presets and New adapters

Dockerfiles adapt to set default model on loading 2

Dockerfiles adapt to set default model on loading

temoin3

Add downloaded files

CMD_FLAGS adapted

CMD_FLAGS Ok

uploader and downloader file

My-LLamandement-fine-tuned Safetensors

test write error

rm LlaMAndement-7b.Q8_0.gguf

Revert "ln cmd on startupt in dockerfile"

LlaMAndement-7b.Q8_0.gguf

ln cmd on startupt in dockerfile

remove flash_attn

add flash-attn with respectful original format

Revert "Update requirements.txt"

Merge branch 'main' of hf.co:spaces/NoQuest/QP_ANmixtao

Revert "Update requirements.txt"

trim lines jump

correction espaces dans version module flash-attn

Update for flash-attn == 2.5.6

Suppr orca

mv old models to orca dir

mistral et adapters sent

add orca model and change config.yaml

Upload adapter_model.bin

adapter_config.json add

Update requirements.txt

Update modules/llama_cpp_python_hijack.py

Update requirements.txt

Update requirements.txt

Update server.py

Update server.py

Update server.py

Update server.py

Update server.py

Update README.md

First version