Kyllene
Collection
Model series for RPG/ERP
•
4 items
•
Updated
•
1
Kyllene 57B v1.0
Model Details
- A result of using SLERP merge of TeeZee/2xbagel-dpo-34b-v0.2 and TeeZee/2xNous-Capybara-34B.
- The resulting model has 100 layers and approximately 57 billion parameters.
- 200K context length
- See mergekit-config.yml for details on the merge method used.
Warning: This model can produce NSFW content!
Results
- produces SFW nad NSFW content without issues, switches context seamlessly.
- good at following instructions
- pretty close to my ideal RPG/ERP everyday model (but more tests are needed)
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 64.86 |
| AI2 Reasoning Challenge (25-Shot) | 64.85 |
| HellaSwag (10-Shot) | 84.51 |
| MMLU (5-Shot) | 73.33 |
| TruthfulQA (0-shot) | 57.89 |
| Winogrande (5-shot) | 78.22 |
| GSM8k (5-shot) | 30.40 |
- Downloads last month
- 2,034
Collection including TeeZee/Kyllene-57B-v1.0
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard64.850
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard84.510
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard73.330
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard57.890
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.220
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard30.400