Testing Might be broken
Collection
testing only models,
•
10 items
•
Updated
•
1
Testing-only don't download
Another trial of merging models with different sizes, still under testing, it's unstable at the moment.
Recipe:
merge_method: task_anysize
base_model: princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT
models:
- model: SanjiWatsuki/Silicon-Maid-7B
parameters:
weight: 0.1
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 35.82 |
| AI2 Reasoning Challenge (25-Shot) | 36.18 |
| HellaSwag (10-Shot) | 51.12 |
| MMLU (5-Shot) | 25.56 |
| TruthfulQA (0-shot) | 44.85 |
| Winogrande (5-shot) | 57.22 |
| GSM8k (5-shot) | 0.00 |
- Downloads last month
- 3,246
Collection including Aryanne/sheared-silicon10p
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard36.180
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard51.120
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard25.560
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard44.850
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard57.220
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.000