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:
15
quantization_config.json
Normal file
15
quantization_config.json
Normal 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": []
|
||||
}
|
||||
Reference in New Issue
Block a user