Improve model card: Add metadata and update paper links and usage snippet

README.md

@@ -1,10 +1,16 @@
+---
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+---
+
 # Explore–Execute Chain (E2C) Model
 
 This repository hosts the **pretrained and fine-tuned Explore–Execute Chain (E2C) models**.
 
-**Paper:** *Explore–Execute Chain: Towards an Efficient Structured Reasoning Paradigm*  
-*Kaisen Yang, Lixuan He, Rushi Shah, Kaicheng Yang, Qinwei Ma, Dianbo Liu, Alex Lamb*  
-> Under review at ICLR 2026  
+**Paper:** [Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm](https://huggingface.co/papers/2509.23946)
+*Kaisen Yang, Lixuan He, Rushi Shah, Kaicheng Yang, Qinwei Ma, Dianbo Liu, Alex Lamb*
+> Under review at ICLR 2026
 
 **Code:** [GitHub – Explore–Execute Chain](https://github.com/yks23/Explore-Execute-Chain)
 
@@ -14,24 +20,24 @@ This repository hosts the **pretrained and fine-tuned Explore–Execute Chain (E
 
 E2C is a **two-stage reasoning framework** designed to improve the efficiency and interpretability of large language models (LLMs):
 
-1. **Exploration** — Generate lightweight reasoning sketches (plans).  
-2. **Execution** — Execute selected plans faithfully for high-quality results.
+1.  **Exploration** — Generate lightweight reasoning sketches (plans).
+2.  **Execution** — Execute selected plans faithfully for high-quality results.
 
 **Benefits:**
-- Efficient reasoning with minimal computation  
-- Explicit, interpretable exploration traces  
-- Easy domain adaptation with minimal supervision  
+- Efficient reasoning with minimal computation
+- Explicit, interpretable exploration traces
+- Easy domain adaptation with minimal supervision
 
 ---
 
 ## 🚀 Key Features
 
-- **Two-stage training**  
-  - **E2C-SFT** — Supervised fine-tuning on exploration–execution pairs  
-  - **E2C-RL** — Reinforcement learning to refine execution  
-- **Efficient adaptation (EF-SFT)** — Adapt with exploration-only data  
-- **Test-time scaling** — Aggregate multiple explorations for better results  
-- Benchmarked on **mathematical** and **medical reasoning** datasets  
+-   **Two-stage training**
+    -   **E2C-SFT** — Supervised fine-tuning on exploration–execution pairs
+    -   **E2C-RL** — Reinforcement learning to refine execution
+-   **Efficient adaptation (EF-SFT)** — Adapt with exploration-only data
+-   **Test-time scaling** — Aggregate multiple explorations for better results
+-   Benchmarked on **mathematical** and **medical reasoning** datasets
 
 ---
 
@@ -39,25 +45,26 @@ E2C is a **two-stage reasoning framework** designed to improve the efficiency an
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
 model_name = "KaisenYang/Explore-Execute-Chain"
 model_type = "8B-Final"  # change to the subfolder you want to use
 
 tokenizer = AutoTokenizer.from_pretrained(model_name, subfolder=model_type)
-model = AutoModelForCausalLM.from_pretrained(model_name, subfolder=model_type)
+model = AutoModelForCausalLM.from_pretrained(model_name, subfolder=model_type, torch_dtype=torch.bfloat16, device_map="auto")
 
 # Test example: Fibonacci sequence
-inputs = tokenizer("What is the 10th number in the Fibonacci sequence?", return_tensors="pt")
+inputs = tokenizer("What is the 10th number in the Fibonacci sequence?", return_tensors="pt").to(model.device)
 outputs = model.generate(**inputs)
 print(tokenizer.decode(outputs[0]))
-````
+```
 
 ---
 
 ## 🔗 Links
 
-* 📂 **Full code and experiments:** [GitHub Repository](https://github.com/yks23/Explore-Execute-Chain)
-* 📜 **Paper (under review):** ICLR 2026 submission
+*   📂 **Full code and experiments:** [GitHub Repository](https://github.com/yks23/Explore-Execute-Chain)
+*   📜 **Paper (under review):** [ICLR 2026 submission](https://huggingface.co/papers/2509.23946)
 
 ---
 
@@ -80,4 +87,4 @@ If you use this work, please cite:
 ## 🧾 License
 
 This project is licensed under the **MIT License**.
-See the [LICENSE](https://github.com/yks23/Explore-Execute-Chain/blob/main/LICENSE) file for details.
+See the [LICENSE](https://github.com/yks23/Explore-Execute-Chain/blob/main/LICENSE) file for details.