Text Generation
Transformers
Safetensors
English
mistral
code
Eval Results
Inference Endpoints
text-generation-inference
uukuguy commited on
Commit
87a4d21
1 Parent(s): 3b6c0f9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -19
README.md CHANGED
@@ -74,28 +74,16 @@ CodeLlama-13B-Python: 42.89
74
 
75
  CodeLlama-13B: 35.07
76
 
77
- ## lm-evaluation-harness
78
-
79
- ```json
80
- {'ARC (acc_norm)': ,
81
- 'HellaSwag (acc_norm)': ,
82
- 'MMLU (acc)': ,
83
- 'TruthfulQA (mc2)': ,
84
- 'Winoground (acc)': ,
85
- 'GSM8K (acc)': ,
86
- 'DROP (f1)': ,
87
- 'Open LLM Score': }
88
- ```
89
 
90
  [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
91
 
92
  | Metric | Value |
93
  | --- | --- |
94
- | ARC | |
95
- | HellaSwag | |
96
- | MMLU | |
97
- | TruthfulQA | |
98
- | Winoground | |
99
- | GSM8K | |
100
- | Average | |
101
 
 
74
 
75
  CodeLlama-13B: 35.07
76
 
 
 
 
 
 
 
 
 
 
 
 
 
77
 
78
  [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
79
 
80
  | Metric | Value |
81
  | --- | --- |
82
+ | ARC | 58.79 |
83
+ | HellaSwag | 81.89 |
84
+ | MMLU | 61.27 |
85
+ | TruthfulQA | 49.85 |
86
+ | Winoground | 78.22 |
87
+ | GSM8K | 56.33 |
88
+ | Average | 64.39 |
89