iproskurina
/

Mistral-7B-v0.3-GPTQ-4bit-g128

Text Generation

4-bit precision

Model card Files Files and versions Community

Mistral-7B-v0.3-GPTQ-4bit-g128 / model.safetensors

Commit History

AutoGPTQ model for mistralai/Mistral-7B-v0.3: 4bits, gr128, desc_act=False

6ae06d4
verified

iproskurina commited on Sep 25

Rename gptq_model-4bit-128g.safetensors to model.safetensors

c7619ba
verified

iproskurina commited on Sep 24