AALF commited on
Commit
6434842
1 Parent(s): 601f2b8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -17
README.md CHANGED
@@ -55,21 +55,4 @@ gradient_checkpointing_kwargs:
55
  use_reentrant: False
56
  ```
57
 
58
- ## Evaluation Results
59
- | Datasets | Llama3.1-8B-Instruct | FuseChat-Llama-3.1-8B-SFT | FuseChat-Llama-3.1-8B-Instruct |
60
- |---------------------------------|----------------------|---------------------------|--------------------------------|
61
- | AlpacaEval-2 (LC/WR) | 28.3/28.7 | 41.3/37.7 | 65.4/63.3 |
62
- | Arena-Hard (WR/SC) | 28.1/23.8 | 38.7/29 | 58.2/46.4 |
63
- | MT-Bench | 8.38 | 8.54 | 9 |
64
- | AlignBench v1.1 | 4.61 | 6.25 | 6.69 |
65
- | LiveBench 0831 | 27.6 | 30.2 | 32 |
66
- | GSM8K | 85.9 | 87 | 88 |
67
- | MATH | 50.7 | 54.7 | 55.2 |
68
- | AMC 23 | 25 | 30 | 37.5 |
69
- | MMLU-Pro | 50 | 47.8 | 49.2 |
70
- | MMLU-redux | 67.2 | 68.4 | 69.2 |
71
- | GPQA-Diamond | 33.8 | 37.9 | 34.9 |
72
- | HumanEval | 69.5 | 69.5 | 71.3 |
73
- | MBPP | 75.4 | 71.4 | 72 |
74
- | LiveCodeBench 2408-2411 (all/esay) | 12.3/40.5 | 12.6/39 | 13.1/43.2 |
75
 
 
55
  use_reentrant: False
56
  ```
57
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58