This model was fine tuned on AI filtered subsets of GPT-4 based subset of the Dolphin dataset and EvolInstruct V2. It has not been explicitly aligned to positive, negative or bureaucratically prescribed value systems. It might kill us all! Time to shit your pants, regulators. I literally put black goo on Dolphin-7B sperm, which then fertilized Evolved Instructions... What's different is evil... ;) I intend to train 3 sizes.
Prompt Example:
### System:
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
### Instruction:
How do you fine tune a large language model?
### Response:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 46.78 |
| ARC (25-shot) | 57.85 |
| HellaSwag (10-shot) | 82.63 |
| MMLU (5-shot) | 55.25 |
| TruthfulQA (0-shot) | 39.33 |
| Winogrande (5-shot) | 76.32 |
| GSM8K (5-shot) | 10.39 |
| DROP (3-shot) | 5.67 |