Instructions to use HopitAI/hopper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use HopitAI/hopper with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B") model = PeftModel.from_pretrained(base_model, "HopitAI/hopper") - Notebooks
- Google Colab
- Kaggle
Hopper v1.1.0: calibration map replaced by one temperature per answer type; adapter weights unchanged
281d393 verified | { | |
| "kind": "per_kind", | |
| "temperatures": { | |
| "choice": 0.7898505975532796, | |
| "noul": 0.7531284680253558, | |
| "score": 0.8997033695617845 | |
| }, | |
| "fitted_on": { | |
| "description": "our own held-out JevBench-style look-alike items, hard tier: three measurement files, 622 items, 536 on the axis. No JevBench item and no JevBench file.", | |
| "tier": "hard", | |
| "map": "per_kind", | |
| "dropped_leakage_flagged": 66 | |
| } | |
| } | |