una-neural-chat-v3-3-phase2
OMA, OneManArmy proudly presents, una-neural-chat-v3-3 PHASE 2. Powered by UNA (Uniform Neural Alignment), using zephyr trainer, allenai/ultrafeedback cleaned.. and JUST THAT.
Outperforming its base model, not adding any data.. just UNA Algorythm on Transformers Lib.
UNA Settings:
- MLP : 0.05
- ATT : 0.03
- LNOR : 0.02
Framework versions
- Transformers 4.35.0-UNA
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 70.72 |
| AI2 Reasoning Challenge (25-Shot) | 67.32 |
| HellaSwag (10-Shot) | 86.33 |
| MMLU (5-Shot) | 63.14 |
| TruthfulQA (0-shot) | 65.49 |
| Winogrande (5-shot) | 79.79 |
| GSM8k (5-shot) | 62.24 |