Files
LLaMA-7b-AWQ/quant_config.json
ModelHub XC 5269b42a50 初始化项目,由ModelHub XC社区提供模型
Model: TheBloke/LLaMA-7b-AWQ
Source: Original Platform
2026-08-28 20:58:13 +08:00

6 lines
90 B
JSON

{
"zero_point": true,
"q_group_size": 128,
"w_bit": 4,
"version": "GEMM"
}