Qwen
/

Qwen-7B-Chat-Int4

Text Generation

4-bit precision

Model card Files Files and versions Community

Qwen-7B-Chat-Int4 / configuration_qwen.py

Commit History

Add ApplyRoPE and RMSNorm kernels written in OpenAI Triton.

af64202

Shangming Cai commited on Dec 5, 2023

softmax_in_fp32

682f4da

yangapku commited on Sep 28, 2023

update kvcache

0e3568a

yangapku commited on Sep 25, 2023

update model

ff5200f

yangapku commited on Sep 25, 2023