GPT2-XL SFT on Deita dataset to change Sams mind. Supports multi-turn dialogue within the range of its capabilities.
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.
### User:
How do you fine tune a large language model?
### Assistant:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 33.91 |
| AI2 Reasoning Challenge (25-Shot) | 29.69 |
| HellaSwag (10-Shot) | 50.27 |
| MMLU (5-Shot) | 26.42 |
| TruthfulQA (0-shot) | 40.38 |
| Winogrande (5-shot) | 56.67 |
| GSM8k (5-shot) | 0.00 |
- Downloads last month
- 363
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for KnutJaegersberg/gpt2-chatbot
Dataset used to train KnutJaegersberg/gpt2-chatbot
Spaces using KnutJaegersberg/gpt2-chatbot 3
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard29.690
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard50.270
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard26.420
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard40.380
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard56.670
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.000