convert ggml-vicuna-7b-f16 to ggml-vicuna-7b-q4_0
Source: https://huggingface.co/chharlesonfire/ggml-vicuna-7b-f16
No unnecessary changes
Usage:
Download llama.cpp from https://github.com/ggerganov/llama.cpp
make and run llama.cpp and choose model with ggml-vicuna-7b-q4_0.bin
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.