Add links for GGUF (v3) models.
The users may directly download llama.cpp compatible GGUF models from our Hugging Face Model Hub.
We mainly provide q2_k, q3_k, q4_0, q4_k, q5_0, q5_k, q6_k, q8_0 quantized types.
Note: As llama.cpp is under active development, the format of the model may change in the future. You are encouraged to convert these models by yourself if model type changes.
Description
Add links for GGUF (v3) models. The users may directly download llama.cpp compatible GGUF models from our Hugging Face Model Hub. We mainly provide
q2_k
,q3_k
,q4_0
,q4_k
,q5_0
,q5_k
,q6_k
,q8_0
quantized types.Note: As llama.cpp is under active development, the format of the model may change in the future. You are encouraged to convert these models by yourself if model type changes.
Related Issue
None.
Explanation of Changes
copilot:walkthrough