Hugging Face's logo

Spaces:
fbaldassarri
/
woq-inference
Sleeping

App Files Community
fbaldassarri commited on
Commit
f928e33
·
verified ·
1 Parent(s): 54d6eb5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -2
README.md CHANGED
@@ -1,3 +1,13 @@
 
 
 
 
 
 
 
 
 
 
1
  # PyTorch Weights-only-Quantization (WoQ)
2
 
3
  Inference scripts for pytorch weights-only-quantization
@@ -28,5 +38,4 @@ For example:
28
 
29
  ```
30
  python teq_inference.py --base meta-llama/Llama-3.2-1B --model_dir ./meta-llama_Llama-3.2-1B-TEQ-int4-gs128-asym --weights_file quantized_weight.pt --config_file qconfig.json --prompt "Tell me a joke" --device cpu
31
- ```
32
-
 
1
+ ---
2
+ license: apache-2.0
3
+ title: PyTorch Weights-only-Quantization (WoQ)
4
+ sdk: gradio
5
+ emoji: 📉
6
+ colorFrom: green
7
+ colorTo: yellow
8
+ pinned: false
9
+ short_description: Inference scripts for pytorch weights-only-quantization
10
+ ---
11
  # PyTorch Weights-only-Quantization (WoQ)
12
 
13
  Inference scripts for pytorch weights-only-quantization
 
38
 
39
  ```
40
  python teq_inference.py --base meta-llama/Llama-3.2-1B --model_dir ./meta-llama_Llama-3.2-1B-TEQ-int4-gs128-asym --weights_file quantized_weight.pt --config_file qconfig.json --prompt "Tell me a joke" --device cpu
41
+ ```