iproskurina
/

Mistral-7B-v0.3-GPTQ2-4bit-g3

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Mistral-7B-v0.3-GPTQ2-4bit-g3 / quantize_config.json

Commit History

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

f5ef914
verified

iproskurina commited on Dec 11, 2024