Instructions to use evalengine/decision-0.8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use evalengine/decision-0.8b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-0.8B") model = PeftModel.from_pretrained(base_model, "evalengine/decision-0.8b") - Notebooks
- Google Colab
- Kaggle
Download provenance/training-summary.json from evalengine/decision-0.8b: direct link, hf CLI and curl.
- Browser
- Download file 435 Bytes
-
https://huggingface.co/evalengine/decision-0.8b/resolve/main/provenance/training-summary.json
- Command line
-
hf download hf://evalengine/decision-0.8b/provenance/training-summary.json
-
curl -L -o training-summary.json https://huggingface.co/evalengine/decision-0.8b/resolve/main/provenance/training-summary.json
435 Bytes
| { | |
| "status": "complete", | |
| "steps": 9289, | |
| "target_steps": 9289, | |
| "full_epochs_requested": 1, | |
| "completed_full_dataset": true, | |
| "trained_tokens": 29185870, | |
| "elapsed_seconds": 1568.275470530003, | |
| "tokens_per_second_including_evaluation": 18610.16801476628, | |
| "peak_gpu_gib": 51.528915882110596, | |
| "adapter": "runs/decision-0.8b-v2/adapter", | |
| "train_sha256": "91d1cd9e1d47e62606300050a718711d4562a7562b34fb8cd4919dbeb8452759" | |
| } | |