Files
Llama-2-70B-Chat-AWQ/quant_config.json
ModelHub XC 2a36c98468 初始化项目,由ModelHub XC社区提供模型
Model: TheBloke/Llama-2-70B-Chat-AWQ
Source: Original Platform
2026-06-06 15:30:12 +08:00

6 lines
90 B
JSON

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