Instructions to use tttx/problem-10-upgrade-torch-ttt-step-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use tttx/problem-10-upgrade-torch-ttt-step-1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-32B") model = PeftModel.from_pretrained(base_model, "tttx/problem-10-upgrade-torch-ttt-step-1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 2.0, | |
| "total_flos": 614948268933120.0, | |
| "train_loss": 0.14902637084014714, | |
| "train_runtime": 1084.9601, | |
| "train_samples": 250, | |
| "train_samples_per_second": 0.461, | |
| "train_steps_per_second": 0.029 | |
| } |