Instructions to use adimyth/compass-lora-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use adimyth/compass-lora-v2 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, "adimyth/compass-lora-v2") - Notebooks
- Google Colab
- Kaggle
Download calibration.json from adimyth/compass-lora-v2: direct link, hf CLI and curl.
- Browser
- Download file 1 kB
-
https://huggingface.co/adimyth/compass-lora-v2/resolve/main/calibration.json
- Command line
-
hf download hf://adimyth/compass-lora-v2/calibration.json
-
curl -L -o calibration.json https://huggingface.co/adimyth/compass-lora-v2/resolve/main/calibration.json
1 kB
| { | |
| "temperatures": { | |
| "choice": 2.0, | |
| "score": 2.0, | |
| "noul": 2.25 | |
| }, | |
| "fitted_on": [ | |
| "dev/splits_v2/calibration-hard.jsonl" | |
| ], | |
| "model": "compass-fusion-lora-qwen3.5-4b-compass-prompt-2", | |
| "readout": "fusion", | |
| "head": null, | |
| "fusion_weight": 0.5, | |
| "n_items": 178, | |
| "report": { | |
| "choice": { | |
| "n": 45, | |
| "fit_half_T": 0.25, | |
| "shipped_T": 2.0, | |
| "held_out_ece_before": 0.0937, | |
| "held_out_ece_after": 0.0931, | |
| "held_out_nll_before": 0.5269, | |
| "held_out_nll_after": 1.2941 | |
| }, | |
| "score": { | |
| "n": 90, | |
| "fit_half_T": 2.25, | |
| "shipped_T": 2.0, | |
| "held_out_ece_before": 0.0286, | |
| "held_out_ece_after": 0.0698, | |
| "held_out_nll_before": 0.0993, | |
| "held_out_nll_after": 0.1376 | |
| }, | |
| "noul": { | |
| "n": 43, | |
| "fit_half_T": 2.0, | |
| "shipped_T": 2.25, | |
| "held_out_ece_before": 0.1522, | |
| "held_out_ece_after": 0.1151, | |
| "held_out_nll_before": 0.5846, | |
| "held_out_nll_after": 0.4233 | |
| } | |
| } | |
| } |