chentianqi commited on
Commit
33be45b
·
verified ·
1 Parent(s): 6ec8604

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -8
README.md CHANGED
@@ -39,14 +39,8 @@ This model has been 4-bit quantized Llada-8B-Base model with [GPTQModel](https:/
39
  - **damp_percent**: 0.1
40
  - **damp_auto_increment**: 0.0015
41
 
42
- ## Benchmark
43
- ### Performance of Quantized Models
44
-
45
- | Dataset | GPTQ-4bit | FP16 |
46
- |----------------|-------------|------|
47
- | mmlu | TODO | 65.9(5) |
48
- | cmmlu | TODO | 69.9(5) |
49
- | arc_challenge | 45.48 | 47.9(0) |
50
 
51
  ## Example:
52
  ```python
 
39
  - **damp_percent**: 0.1
40
  - **damp_auto_increment**: 0.0015
41
 
42
+
43
+
 
 
 
 
 
 
44
 
45
  ## Example:
46
  ```python