Add model card

README.md

@@ -0,0 +1,55 @@
+---
+license: mit
+base_model: meta-llama/Llama-3.2-1B-Instruct
+language:
+  - en
+tags:
+  - latent-reasoning
+  - interpretability
+  - reasoning
+  - multimode_codi
+  - prontoqa
+---
+
+# Multi-mode CODI · llama32-1b · PrOntoQA
+
+This is the **Multi-mode CODI** checkpoint trained on **PrOntoQA** with base model
+[`meta-llama/Llama-3.2-1B-Instruct`](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct), from the paper
+[*Are Latent Reasoning Models Easily Interpretable?*](https://arxiv.org/abs/2604.04902) (Dilgren & Wiegreffe, 2026).
+
+- 📄 **Paper:** https://arxiv.org/abs/2604.04902
+- 💻 **Code:** https://github.com/connordilgren/are-lrms-easily-interpretable
+- 📚 **Collection (all checkpoints):** https://huggingface.co/collections/connordilgren/are-latent-reasoning-models-easily-interpretable-6a46a3c39b0045c223b15a89
+
+## Files
+
+This repository contains a single raw PyTorch checkpoint, **`pytorch_model.bin`** — the state dict as
+saved by the training framework. It is not a `from_pretrained`-style model; it is loaded by
+the paper's evaluation code, which builds the base model and applies this checkpoint.
+
+## Usage
+
+The evaluation code in the [repository](https://github.com/connordilgren/are-lrms-easily-interpretable) loads this checkpoint from the local path
+configured in `model_paths.yaml`. Download it to the expected location with:
+
+```bash
+hf download connordilgren/llama32-1b-prontoqa-multimode-codi pytorch_model.bin --local-dir checkpoints/codi_trained_models/prontoqa_llama1b_direct_answer/Llama-3.2-1B-Instruct/ep_20/lr_0.0008/seed_11/best_checkpoint
+```
+
+This places the file at `checkpoints/codi_trained_models/prontoqa_llama1b_direct_answer/Llama-3.2-1B-Instruct/ep_20/lr_0.0008/seed_11/best_checkpoint/pytorch_model.bin`, which is the path referenced for this model
+(`llama` → `prontoqa` → `multimode_codi`) in `model_paths.yaml`. See the
+repository README for full setup and evaluation instructions.
+
+## Citation
+
+```bibtex
+@misc{dilgren2026latentreasoningmodelseasily,
+      title={Are Latent Reasoning Models Easily Interpretable?},
+      author={Connor Dilgren and Sarah Wiegreffe},
+      year={2026},
+      eprint={2604.04902},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2604.04902},
+}
+```