jjaegii
/

Llama-3.1-8B-LoRA-kolon-sg-v2-merged-GPTQ-INT4

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Llama-3.1-8B-LoRA-kolon-sg-v2-merged-GPTQ-INT4 / gptq_model-4bit-128g.safetensors

Commit History

AutoGPTQ model for jjaegii/Llama-3.1-8B-LoRA-kolon-sg-v2-merged: 4bits, gr128, desc_act=False

8418b2a
verified

jjaegii commited on 11 days ago