Improve model card: Add library, update pipeline tag, link to code

This PR improves the model card by:

- Updating the `pipeline_tag` to `text-generation` to accurately reflect the model's capabilities in reasoning and code generation.
- Adding `library_name: transformers` to indicate compatibility with the Hugging Face Transformers library.
- Adding a direct link to the GitHub repository for easier access to the code.

README.md

@@ -1,26 +1,60 @@
 ---
 base_model:
 - allenai/OLMo-2-1124-7B-SFT
-license: apache-2.0
 datasets:
 - math
+language:
+- en
+license: apache-2.0
 metrics:
 - accuracy
 pipeline_tag: text-generation
-language:
-- en
+library_name: transformers
 ---
 
 # OLMo-2-7B-SFT-Intuitor-MATH-1EPOCH
 
-**Description:**  
+This repository contains the `OLMo-2-7B-SFT-Intuitor-MATH-1EPOCH` model, an Intuitor-fine-tuned version of `Allenai/OLMo-2-1124-7B-SFT` trained on the MATH dataset, as presented in the paper [Learning to Reason without External Rewards](https://huggingface.co/papers/2505.19590).
 
-An Intuitor-fine-tuned version of Allenai/OLMo-2-1124-7B-SFT trained on the MATH dataset.
+**Intuitor** is a reinforcement learning method that fine-tunes Large Language Models (LLMs) using *self-certainty*—the model’s own internal confidence—as the sole reward. It is built on a novel paradigm called **Reinforcement Learning from Internal Feedback (RLIF)**, enabling models to learn without any external rewards, gold labels, or verifiers.
 
----
+## Usage
+
+You can load this model using the Hugging Face `transformers` library. For detailed instructions on how to use, train, and evaluate the model, please refer to the official GitHub repository:
+
+[**GitHub Repository: sunblaze-ucb/Intuitor**](https://github.com/sunblaze-ucb/Intuitor)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the model and tokenizer
+model_name = "sunblaze-ucb/OLMo-2-7B-SFT-Intuitor-MATH-1EPOCH"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
+
+# Example for text generation
+prompt = "Question: What is 2 + 2?
+Answer:"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=50,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.9,
+    eos_token_id=tokenizer.eos_token_id
+)
+
+generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(generated_text)
+```
 
 ## Citation
 
+If you find our work helpful or inspiring, please feel free to cite it:
+
 ```bibtex
 @article{zhao2025learning,
   title={Learning to Reason without External Rewards},