Improve model card: Add pipeline tag, paper link, code link, and sample usage

README.md

@@ -1,10 +1,32 @@
 ---
-library_name: transformers
-license: llama3.2
 base_model: meta-llama/Llama-3.2-1B-Instruct
 datasets:
 - whynlp/gsm8k-aug
+library_name: transformers
+license: llama3.2
 tags: []
+pipeline_tag: text-generation
 ---
 
-Built with Llama
+# Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning
+
+This repository contains the `Llama-adaLR-model-latent-6_rl` model, developed as part of the paper [Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning](https://huggingface.co/papers/2511.21581).
+
+This model introduces adaptive-length latent reasoning models and a post-SFT reinforcement-learning methodology to optimize latent reasoning length by minimizing reasoning length while maintaining accuracy, demonstrating a significant drop in total reasoning length with no penalty to accuracy on the Llama 3.2 1B model and the GSM8K-Aug dataset.
+
+Code: https://github.com/apning/adaptive-latent-reasoning
+
+## Sample Usage
+
+You can load these models using the function `automodelforcausallm_from_pretrained_latent` from `src.model_creation`, as demonstrated below:
+
+```python
+from transformers import AutoTokenizer
+from src.model_creation import automodelforcausallm_from_pretrained_latent
+
+repo_id = "Lapisbird/Llama-adaLR-model-latent-6" # or use "Lapisbird/Llama-adaLR-model-latent-6_rl" for the RL-tuned version
+
+model = automodelforcausallm_from_pretrained_latent(repo_id)
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+```
+For more detailed instructions and other model checkpoints, please refer to the [GitHub repository](https://github.com/apning/adaptive-latent-reasoning).