Hugging Face's logo

Dongwei
/
Rationalyst_reasoning_datasets

Text Generation
Transformers
Safetensors
llama
feature-extraction
conversational
text-generation-inference
Model card Files Community
3
Dongwei commited on
Commit
f0098eb
·
verified ·
1 Parent(s): 4d16990

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -30,4 +30,4 @@ When used to evaluate on downstream tasks, this model achieves the following res
30
 
31
  | Task | GSM8K | MATH | ECQA | HellaSwag | ProofWriter | ARC | MMLU-Pro |
32
  |:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|:----:|
33
- | | 76.2 | 32.5 | 76.2 | 59.4 | 90.1 | 79.3 | 32.1 |
 
30
 
31
  | Task | GSM8K | MATH | ECQA | HellaSwag | ProofWriter | ARC | MMLU-Pro |
32
  |:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|:----:|
33
+ | | 80.3 | 31.4 | 74.5 | 59.1 | 88.2 | 78.8 | 41.2 |