Instructions to use Tina-Yi/R1-Distill-Qwen-1.5B-OpenR1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Tina-Yi/R1-Distill-Qwen-1.5B-OpenR1 with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
no info about how to use them
#1
by asmodun - opened
nothing is in the model card , are we supposed to use them or what , thanks
Hey, thanks for the question!
Tina models are essentially just LoRA adapters over the base model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. You can use them via standard peft-based loading.
We will update the model cards in the near future after some recent deadlines, please stay tuned :-)
Hey, now all Tina model cards are all updated, feel free to check them out! (sorry for the delay feedback though)