初始化项目,由ModelHub XC社区提供模型

Model: Vishva007/Qwen3-4B-Instruct-2507-W4A16-AutoRound-AWQ
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-24 18:58:11 +08:00
commit 70961dc54b
13 changed files with 152015 additions and 0 deletions

15
quantization_config.json Normal file
View File

@@ -0,0 +1,15 @@
{
"bits": 4,
"group_size": 128,
"sym": true,
"data_type": "int",
"batch_size": 4,
"iters": 1000,
"nsamples": 512,
"autoround_version": "0.9.7",
"provider": "auto-round",
"quant_method": "awq",
"zero_point": false,
"version": "gemm",
"modules_to_not_convert": []
}