Instructions to use golaxy/ReDI_Interpretation_Sparse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use golaxy/ReDI_Interpretation_Sparse with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/root/paddlejob/workspace/env_run/output/llm/Qwen3-8B") model = PeftModel.from_pretrained(base_model, "golaxy/ReDI_Interpretation_Sparse") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 3.0, | |
| "total_flos": 6.751297376408863e+17, | |
| "train_loss": 0.4856139095743696, | |
| "train_runtime": 18496.859, | |
| "train_samples_per_second": 0.776, | |
| "train_steps_per_second": 0.097 | |
| } |