Text Generation
Transformers
Safetensors
English
doge
conversational
custom_code
JingzeShi commited on
Commit
0688582
·
verified ·
1 Parent(s): 73c5dce

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -45,10 +45,10 @@ In addition, Doge uses Dynamic Mask Attention as sequence transformation and can
45
 
46
  **Evaluation**:
47
 
48
- | Model | MMLU | TriviaQA | ARC-E | ARC-C | PIQA | HellaSwag | OBQA | Winogrande |
49
- |---|---|---|---|---|---|---|---|---|
50
- | [Doge-20M](https://huggingface.co/JingzeShi/Doge-20M) | 25.43 | 0 | 36.83 | 22.53 | 58.38 | 27.25 | 25.60 | 50.20 |
51
- | [Doge-60M](https://huggingface.co/JingzeShi/Doge-60M) | 26.41 | 0 | 50.00 | 25.34 | 61.43 | 31.45 | 28.00 | 49.64 |
52
 
53
  > All evaluations are done using five-shot settings, without additional training on the benchmarks.
54
 
 
45
 
46
  **Evaluation**:
47
 
48
+ | Model | MMLU | TriviaQA | ARC-E | ARC-C | PIQA | HellaSwag | OBQA | Winogrande | tokens / s on CPU |
49
+ |---|---|---|---|---|---|---|---|---|---|
50
+ | [Doge-20M](https://huggingface.co/JingzeShi/Doge-20M) | 25.43 | 0 | 36.83 | 22.53 | 58.38 | 27.25 | 25.60 | 50.20 | 142 |
51
+ | [Doge-60M](https://huggingface.co/JingzeShi/Doge-60M) | 26.41 | 0 | 50.00 | 25.34 | 61.43 | 31.45 | 28.00 | 49.64 | 62 |
52
 
53
  > All evaluations are done using five-shot settings, without additional training on the benchmarks.
54