SuperBruphin-3x7B
This is an experimental MoE model created using mergekit. (mixtral branch)
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: nbeerbower/bruphin-epsilon
gate_mode: hidden
dtype: bfloat16
experts:
- source_model: nbeerbower/bruphin-epsilon
positive_prompts:
- "Tell a story."
- source_model: FelixChao/WestSeverus-7B-DPO-v2
positive_prompts:
- "Solve this problem."
- source_model: jondurbin/airoboros-m-7b-3.1.2
positive_prompts:
- "Write a letter."
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 73.75 |
| AI2 Reasoning Challenge (25-Shot) | 71.16 |
| HellaSwag (10-Shot) | 87.74 |
| MMLU (5-Shot) | 64.58 |
| TruthfulQA (0-shot) | 66.85 |
| Winogrande (5-shot) | 81.53 |
| GSM8k (5-shot) | 70.66 |
- Downloads last month
- 66
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for nbeerbower/SuperBruphin-3x7B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard71.160
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard87.740
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.580
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard66.850
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard81.530
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard70.660