Smaug Dolphin 60B
This model is a MoErge of abacusai/Smaug-34B-v0.1 and cognitivecomputations/dolphin-2.2-yi-34b-200k
This model works as expected. Evaluations are running now.
GGUF + iMatrix
Available here
AWQ
TODO
Example output
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 76.44 |
AI2 Reasoning Challenge (25-Shot) | 73.38 |
HellaSwag (10-Shot) | 86.55 |
MMLU (5-Shot) | 76.78 |
TruthfulQA (0-shot) | 67.44 |
Winogrande (5-shot) | 83.50 |
GSM8k (5-shot) | 70.96 |
- Downloads last month
- 614
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard73.380
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard86.550
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard76.780
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard67.440
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard83.500
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard70.960