CausalLM trained for 3 epochs on playtypus dataset with NEFTune.
Both Llama2 and Qwen licenses apply, find them in the attached files.
Prompt Example:
### Instruction:
What is AGI?
### Response:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 63.80 |
| AI2 Reasoning Challenge (25-Shot) | 56.91 |
| HellaSwag (10-Shot) | 80.06 |
| MMLU (5-Shot) | 64.98 |
| TruthfulQA (0-shot) | 47.57 |
| Winogrande (5-shot) | 76.01 |
| GSM8k (5-shot) | 57.24 |
- Downloads last month
- 1,359
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Dataset used to train KnutJaegersberg/CausalLM-Platypus-14B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard56.910
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard80.060
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.980
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard47.570
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard76.010
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard57.240