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: senseable/WestLake-7B-v2
parameters:
weight: 1.0
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 41.16 |
| AI2 Reasoning Challenge (25-Shot) | 39.76 |
| HellaSwag (10-Shot) | 70.33 |
| MMLU (5-Shot) | 26.81 |
| TruthfulQA (0-shot) | 46.50 |
| Winogrande (5-shot) | 63.54 |
| GSM8k (5-shot) | 0.00 |
- Downloads last month
- 3,560
Collection including Aryanne/sheared-plus-westlake-normal
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard39.760
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard70.330
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard26.810
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard46.500
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard63.540
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.000