Testing Might be broken
Collection
testing only models,
•
10 items
•
Updated
•
1
Another trial of merging models with different sizes, still under testing, should be more stable, but I have no ideia if it's improving or degrading the base model.
Recipe:
merge_method: task_anysize
base_model: princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT
models:
- model: KoboldAI/Mistral-7B-Erebus-v3
parameters:
weight: 0.5
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 41.85 |
| AI2 Reasoning Challenge (25-Shot) | 40.70 |
| HellaSwag (10-Shot) | 71.04 |
| MMLU (5-Shot) | 28.06 |
| TruthfulQA (0-shot) | 47.40 |
| Winogrande (5-shot) | 63.93 |
| GSM8k (5-shot) | 0.00 |
- Downloads last month
- 3,577
Collection including Aryanne/ereb-test
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard40.700
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard71.040
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard28.060
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard47.400
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard63.930
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.000