pavfi-at-m
/

gpt2GPTQ8

Text Generation

Inference Endpoints

Model card Files Files and versions Community

gpt2GPTQ8 / quantize_config.json

Commit History

GPT2gpt2: 8bits, gr-1, desc_act=False

ce619c3

pavfi-at-m commited on Oct 27, 2023

GPT2gpt2: 8bits, gr128, desc_act=False

d09383d

pavfi-at-m commited on Oct 27, 2023