Add model card for Reasoning Cache (RCT-4B)

This PR adds a comprehensive model card for the `RCT-4B` model, which implements the Reasoning Cache (RC) algorithm.

Key improvements include:
- Added `pipeline_tag: text-generation` for better discoverability.
- Added `library_name: transformers` to enable the automated `transformers` code snippet, as the model architecture is compatible.
- Included relevant `tags` such as `reasoning`, `extrapolation`, `rl`, and `qwen`.
- Provided a clear model description based on the paper abstract.
- Linked to the official research paper: [Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL](https://huggingface.co/papers/2602.03773).
- Added a link to the official GitHub repository: [IanYHWu/rc](https://github.com/IanYHWu/rc).
- Included a usage section explaining the need for RC-decoding logic, referencing vLLM for inference and verl for training, and clarifying `transformers` compatibility for loading.
- Added a BibTeX citation.

This enhanced model card provides essential information for users and improves the model's integration and discoverability on the Hugging Face Hub.

README.md

@@ -0,0 +1,53 @@
+---
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- reasoning
+- extrapolation
+- rl
+- qwen
+---
+
+# Reasoning Cache (RCT-4B)
+
+This repository contains the `RCT-4B` model checkpoint, a 4B parameter Large Language Model (LLM) trained using **Reasoning Cache (RC)**, as introduced in the paper [Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL](https://huggingface.co/papers/2602.03773).
+
+## Model Description
+
+Reasoning Cache (RC) is an iterative decoding algorithm that replaces standard autoregressive decoding during both training and inference. It exploits an asymmetry between the response generation and summarization capabilities of LLMs to construct reasoning chains that consistently improve across iterations.
+
+Models trained to use RC can extrapolate and continually improve over reasoning horizons significantly longer than those seen during training. Empirically, `RCT-4B` demonstrates substantial performance gains on challenging benchmarks like HMMT 2025, outperforming both comparably sized models and many larger reasoning LLMs by effectively scaling test-time compute.
+
+*   **Developed by:** Ian Wu, Yuxiao Qu, Amrith Setlur, Aviral Kumar
+*   **Paper:** [Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL](https://huggingface.co/papers/2602.03773)
+*   **Repository:** [GitHub - IanYHWu/rc](https://github.com/IanYHWu/rc)
+
+## Usage
+
+This model can be loaded using the Hugging Face `transformers` library for standard model and tokenizer operations. However, to leverage the iterative `RC`-decoding algorithm and achieve the continual improvement and extrapolation capabilities described in the paper, specific inference logic must be applied.
+
+For detailed instructions on using `RC`-decoding for inference (which currently supports `vLLM`) and for the training code (which requires `verl`), please refer to the [official GitHub repository](https://github.com/IanYHWu/rc).
+
+```python
+# Example of loading the model with transformers (RC-decoding logic not included here)
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_name = "YOUR_REPO_ID_HERE" # Replace with the actual repository ID
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# For RC-decoding, please refer to the official GitHub repository's `inference` section.
+```
+
+## Citation
+
+If you find this work useful, please cite the original paper:
+
+```bibtex
+@article{wu2026reasoning,
+  title={Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL},
+  author={Wu, Ian and Qu, Yuxiao and Setlur, Amrith and Kumar, Aviral},
+  journal={arXiv preprint arXiv:2602.03773},
+  year={2026}
+}
+```