初始化项目,由ModelHub XC社区提供模型
Model: umyunsang/GovOn-EXAONE-AWQ-v2 Source: Original Platform
This commit is contained in:
18
quantization_log.json
Normal file
18
quantization_log.json
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"stage": "2_awq_quantization_v2",
|
||||
"timestamp": "2026-03-19T10:52:52.952927",
|
||||
"merged_model_dir": "/content/models/merged_model",
|
||||
"output_dir": "/content/models/awq_quantized_model",
|
||||
"quant_config": {
|
||||
"zero_point": true,
|
||||
"q_group_size": 128,
|
||||
"w_bit": 4,
|
||||
"version": "GEMM"
|
||||
},
|
||||
"calibration_samples": 512,
|
||||
"awq_model_size_gb": 4.940028339624405,
|
||||
"merged_model_size_gb": 14.563027188181877,
|
||||
"compression_ratio": 2.947964300400981,
|
||||
"size_reduction_pct": 66.07828663786802,
|
||||
"quantization_time_seconds": 1117.1531629562378
|
||||
}
|
||||
Reference in New Issue
Block a user