Blur-7b-slerp-v1.41
Blur-7b-slerp-v1.41 is a merge of the following models using mergekit:
🧩 Configuration
slices:
- sources:
- model: bardsai/jaskier-7b-dpo-v5.6
layer_range: [0, 32]
- model: liminerity/merge
layer_range: [0, 32]
merge_method: slerp
base_model: bardsai/jaskier-7b-dpo-v5.6
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16
#im pretty sure this will be bricked so
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 75.98 |
| AI2 Reasoning Challenge (25-Shot) | 72.78 |
| HellaSwag (10-Shot) | 88.65 |
| MMLU (5-Shot) | 64.84 |
| TruthfulQA (0-shot) | 74.23 |
| Winogrande (5-shot) | 83.90 |
| GSM8k (5-shot) | 71.49 |
- Downloads last month
- 2,632
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard72.780
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard88.650
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.840
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard74.230
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard83.900
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard71.490