Instructions to use effcot/Limo_llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use effcot/Limo_llama with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct") model = PeftModel.from_pretrained(base_model, "effcot/Limo_llama") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.7616215348243713, | |
| "eval_runtime": 13.6304, | |
| "eval_samples_per_second": 2.935, | |
| "eval_steps_per_second": 0.734, | |
| "total_flos": 3.853307493895635e+18, | |
| "train_loss": 0.7713966806729634, | |
| "train_runtime": 10792.2617, | |
| "train_samples_per_second": 0.704, | |
| "train_steps_per_second": 0.011 | |
| } |