flammen
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the TIES merge method using bardsai/jaskier-7b-dpo-v5.6 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: bardsai/jaskier-7b-dpo-v5.6
- model: nbeerbower/bruphin-zeta
parameters:
density: 0.5
weight: 0.5
- model: Gille/StrangeMerges_16-7B-slerp
parameters:
density: 0.5
weight: 0.3
merge_method: ties
base_model: bardsai/jaskier-7b-dpo-v5.6
parameters:
normalize: true
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 71.74 |
| AI2 Reasoning Challenge (25-Shot) | 68.17 |
| HellaSwag (10-Shot) | 87.06 |
| MMLU (5-Shot) | 64.68 |
| TruthfulQA (0-shot) | 63.02 |
| Winogrande (5-shot) | 81.45 |
| GSM8k (5-shot) | 66.03 |
- Downloads last month
- 1,383
Merge of
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard68.170
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard87.060
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.680
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard63.020
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard81.450
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard66.030