Instructions to use KnutJaegersberg/RWKV-4-PilePlus-1B5-20230520-2942-486Gtokens-ctx4096 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KnutJaegersberg/RWKV-4-PilePlus-1B5-20230520-2942-486Gtokens-ctx4096 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("KnutJaegersberg/RWKV-4-PilePlus-1B5-20230520-2942-486Gtokens-ctx4096", dtype="auto") - Notebooks
- Google Colab
- Kaggle
This is just a standard conversion to hf transformers format of models from here:
https://huggingface.co/BlinkDL/rwkv-4-pileplus
According to the documentation I found, this model should have seen roundabout roundabout 0.8 trillion tokens!
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 28.77 |
| ARC (25-shot) | 30.63 |
| HellaSwag (10-shot) | 52.63 |
| MMLU (5-shot) | 25.04 |
| TruthfulQA (0-shot) | 34.96 |
| Winogrande (5-shot) | 52.8 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 5.33 |
- Downloads last month
- 107
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support