base_model: mistralai/Mistral-7B-Instruct-v0.2 gate_mode: hidden # one of "hidden", "cheap_embed", or "random" dtype: bfloat16 # output dtype (float32, float16, or bfloat16) experts: - source_model: SanjiWatsuki/Kunoichi-DPO-v2-7B positive_prompts: - "roleplay" - source_model: mistralai/Mistral-7B-Instruct-v0.2 positive_prompts: - "chat"
chatml
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 68.47 |
| AI2 Reasoning Challenge (25-Shot) | 66.89 |
| HellaSwag (10-Shot) | 85.69 |
| MMLU (5-Shot) | 62.65 |
| TruthfulQA (0-shot) | 66.80 |
| Winogrande (5-shot) | 77.35 |
| GSM8k (5-shot) | 51.40 |
- Downloads last month
- 862
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for LoSboccacc/orthogonal-2x7B-v2-base
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard66.890
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.690
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard62.650
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard66.800
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard77.350
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard51.400