File size: 296 Bytes
43a66d3
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
import torch

blob_path = "./llama-2-chat-7b_r0.8_g128.pth"

blob = torch.load(blob_path)

for layer, attr in blob.items():
    print(f"{layer:30} | q_dtype: {attr['q_dtype']:5} | orig. shape: {str(attr['original_shape']):15} | quantized_shape: {str(attr['q_weight'].shape):15}")


print("done.")