stan-hua
/

Qwen2-7B-Instruct-AWQ-W4A16

4-bit precision

Model card Files Files and versions Community

Qwen2-7B-Instruct-AWQ-W4A16 / special_tokens_map.json

Commit History

AWQ model for Qwen/Qwen2-7B-Instruct: {'w_bit': 4, 'zero_point': True, 'q_group_size': 128, 'version': 'GEMM'}

45dd1c1
verified

stan-hua commited on 11 days ago