Improve model card: Add library, links, and usage example

This PR significantly enhances the model card for `sunblaze-ucb/Qwen3-14B-GRPO-MATH-1EPOCH` by:

* Updating the main heading to reflect the full model ID: `sunblaze-ucb/Qwen3-14B-GRPO-MATH-1EPOCH`.
* Adding `library_name: transformers` to the metadata, enabling the "how to use" widget and improving discoverability.
* Including descriptive `tags` such as `reinforcement-learning`, `llm`, `reasoning`, and `math` for better categorization.
* Providing an expanded model description based on the paper abstract and project details, giving users a better understanding of the model and the underlying "Intuitor" and "RLIF" frameworks.
* Adding explicit links to the paper, the project page, and the GitHub repository for easy access to source materials and code.
* Including a clear Python code snippet for sample usage with the `transformers` library, making it easier for users to get started with inference.

Please review and merge this PR to improve the model's visibility and usability on the Hugging Face Hub.

README.md

@@ -1,25 +1,82 @@
 ---
 base_model: Qwen/Qwen3-14B
-license: apache-2.0
 datasets:
-  - math
+- math
+language:
+- en
+license: apache-2.0
 metrics:
-  - accuracy
+- accuracy
 pipeline_tag: text-generation
-language:
-  - en
+library_name: transformers
+tags:
+- reinforcement-learning
+- llm
+- reasoning
+- math
 ---
 
-# Qwen/Qwen3-14B-GRPO-MATH-1EPOCH
+# sunblaze-ucb/Qwen3-14B-GRPO-MATH-1EPOCH
+
+[📄 Paper](https://huggingface.co/papers/2505.19590) | [🌐 Project Page](https://sites.google.com/view/eagle-llm) | [💻 GitHub](https://github.com/sunblaze-ucb/intuitor)
+
+**Description:**
 
-**Description:**  
+This model is a GRPO-fine-tuned version of Qwen3-14B, specifically trained on the MATH dataset. It is part of the **Intuitor** project, presented in the paper "Learning to Reason without External Rewards".
 
-A GRPO-fine-tuned version of Qwen3-14B trained on the MATH dataset.
+**Intuitor** is a novel reinforcement learning method that leverages *self-certainty*—the model’s own internal confidence—as its sole reward signal to fine-tune large language models (LLMs). This approach falls under a new framework called **Reinforcement Learning from Internal Feedback (RLIF)**, which enables LLMs to learn effectively from intrinsic signals, circumventing the need for costly external rewards, gold labels, or verifiers. This makes RLIF a scalable and domain-agnostic alternative to traditional RL methods, particularly useful when verifiable rewards are unavailable.
+
+This particular model demonstrates Intuitor's ability to match GRPO's performance on mathematical benchmarks while showing superior generalization to out-of-domain tasks like code generation, all without requiring gold solutions or test cases.
+
+---
+
+## Usage
+
+You can use this model with the `transformers` library for text generation.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "sunblaze-ucb/Qwen3-14B-GRPO-MATH-1EPOCH"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True
+)
+model.eval()
+
+# Example using a chat-like template, typical for instruction-tuned models like Qwen.
+# Adjust prompt format as needed for your specific use case.
+messages = [
+    {"role": "user", "content": "Question: Solve the following equation: $x + 7 = 15$. Show your steps. Answer:"}
+]
+
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    model_inputs.input_ids,
+    max_new_tokens=100,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.9,
+    eos_token_id=tokenizer.eos_token_id
+)
+
+generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
+print(generated_text)
+```
 
 ---
 
 ## Citation
 
+If you use Intuitor in your research, please cite our paper:
+
 ```bibtex
 @article{zhao2025learning,
   title   = {Learning to Reason without External Rewards},
@@ -27,4 +84,4 @@ A GRPO-fine-tuned version of Qwen3-14B trained on the MATH dataset.
   journal = {arXiv preprint arXiv:2505.19590},
   year    = {2025}
 }
-```
+```