iproskurina
/

opt-125m-gptq2

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

opt-125m-gptq2 / quantize_config.json

Commit History

AutoGPTQ model for facebook/opt-125m: 4 bits, gr128, desc_act=False

186b371
verified

iproskurina commited on 25 days ago