Abhaykoul commited on
Commit
40e04bd
1 Parent(s): 004d595

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -9
README.md CHANGED
@@ -134,13 +134,14 @@ print(generated_text)
134
  # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
135
  Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_OEvortex__vortex-3b)
136
 
137
- | Metric |Value|
138
- |---------------------------------|----:|
139
- |Avg. |35.76|
140
- |AI2 Reasoning Challenge (25-Shot)|31.91|
141
- |HellaSwag (10-Shot) |56.89|
142
- |MMLU (5-Shot) |27.32|
143
- |TruthfulQA (0-shot) |37.39|
144
- |Winogrande (5-shot) |60.14|
145
- |GSM8k (5-shot) | 0.91|
 
146
 
 
134
  # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
135
  Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_OEvortex__vortex-3b)
136
 
137
+
138
+ | Metric | vortex 3b | vortex 3b-v2 | dolly-v2-3b | pythia-2.8b-deduped |
139
+ |---------|----------:|-------------:|------------------:|----------------------------------:|
140
+ | Avg. | 35.76 | 37.46 | 25.26 | 36.72 |
141
+ | AI2 Reasoning Challenge (25-Shot) | 31.91 | 39.68 | 22.83 | 36.26 |
142
+ | HellaSwag (10-Shot) | 56.89 | 65.04 | 26.55 | 60.66 |
143
+ | MMLU (5-Shot) | 27.32 | 25.09 | 24.7 | 26.78 |
144
+ | TruthfulQA (0-shot) | 37.39 | 33.80 | 0 | 35.56 |
145
+ | Winogrande (5-shot) | 60.14 | 59.12 | 59.43 | 60.22 |
146
+ | GSM8k (5-shot) | 0.91 | 2.05 | 1.86 | 0.83 |
147