Files
Llama-2-7B-Chat-AWQ/quant_config.json
ModelHub XC 8fdfae2401 初始化项目,由ModelHub XC社区提供模型
Model: TheBloke/Llama-2-7B-Chat-AWQ
Source: Original Platform
2026-05-29 23:15:15 +08:00

6 lines
90 B
JSON

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