Made for the purpose of comparison with the tinyllama model. 3 epochs, neftune on trilobite.
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. | 35.02 |
AI2 Reasoning Challenge (25-Shot) | 32.94 |
HellaSwag (10-Shot) | 57.24 |
MMLU (5-Shot) | 25.26 |
TruthfulQA (0-shot) | 38.49 |
Winogrande (5-shot) | 55.88 |
GSM8k (5-shot) | 0.30 |
- Downloads last month
- 1,375
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.
Dataset used to train KnutJaegersberg/falcon-1b-t-sft
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard32.940
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard57.240
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard25.260
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard38.490
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard55.880
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.300