venera-ai
/

SeaLLM-7B-v2.5-4bit

Text Generation

4-bit precision

Model card Files Files and versions Community

SeaLLM-7B-v2.5-4bit / quantize_config.json

Commit History

AutoGPTQ model for SeaLLMs/SeaLLM-7B-v2.5: 4bits, gr128, desc_act=False

1cb3654
verified

tminh commited on Apr 26, 2024