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 README.md from adimyth/compass-lora-v2: direct link, hf CLI and curl.
- Browser
- Download file 597 Bytes
-
https://huggingface.co/adimyth/compass-lora-v2/resolve/main/README.md
- Command line
-
hf download hf://adimyth/compass-lora-v2/README.md
-
curl -L -o README.md https://huggingface.co/adimyth/compass-lora-v2/resolve/main/README.md
597 Bytes
metadata
base_model: Qwen/Qwen3.5-4B
library_name: peft
license: apache-2.0
tags:
- lora
- decision-model
- compass
LoRA adapter for Compass compass-0.2.0: rank 16 on the attention and MLP projections of Qwen3.5-4B (revision 851bf6e8), trained through Compass's verification and direct readouts on its own generated and drafted decision items. Load it through the Compass server (scripts/serve.sh), which merges it at start; calibration.json holds the matching per-type temperatures. Results and method: the repository README and docs/EXPERIMENTS.md.