Merge
Collection
All created merge models.
•
3 items
•
Updated
MysticFusion-13B
YAML:
models:
- model: KoboldAI/LLaMA2-13B-Tiefighter
parameters:
weight: 0.3
- model: NeverSleep/Noromaid-13b-v0.1.1
parameters:
weight: 0.5
- model: lmsys/vicuna-13b-v1.5
parameters:
weight: 0.2
merge_method: linear
dtype: float16
Usage:
This is meant to be story writing and basic instruction. More of story writing.
Prompt Template:
Alpaca
### Instruction:
### Response:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 59.31 |
| AI2 Reasoning Challenge (25-Shot) | 61.35 |
| HellaSwag (10-Shot) | 84.43 |
| MMLU (5-Shot) | 57.29 |
| TruthfulQA (0-shot) | 51.98 |
| Winogrande (5-shot) | 76.01 |
| GSM8k (5-shot) | 24.79 |
- Downloads last month
- 3,064
Collection including Walmart-the-bag/MysticFusion-13B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard61.350
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard84.430
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard57.290
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard51.980
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard76.010
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard24.790