初始化项目,由ModelHub XC社区提供模型
Model: Intel/gemma-2b-int4-inc Source: Original Platform
This commit is contained in:
20
quantize_config.json
Normal file
20
quantize_config.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"bits": 4,
|
||||
"group_size": 128,
|
||||
"damp_percent": 0.01,
|
||||
"desc_act": false,
|
||||
"static_groups": false,
|
||||
"sym": false,
|
||||
"true_sequential": false,
|
||||
"model_name_or_path": null,
|
||||
"model_file_base_name": "model",
|
||||
"is_marlin_format": false,
|
||||
"quant_method": "intel/auto-round",
|
||||
"autoround_version": "0.2.0.dev",
|
||||
"iters": 400,
|
||||
"lr": 0.0025,
|
||||
"minmax_lr": 0.0025,
|
||||
"enable_minmax_tuning": true,
|
||||
"enable_quanted_input": true,
|
||||
"scale_dtype": "float16"
|
||||
}
|
||||
Reference in New Issue
Block a user