Update README.md

README.md

@@ -1,58 +1,21 @@
 ---
-base_model: Qwen/Qwen2.5-32B-Instruct
-library_name: transformers
-model_name: Qwen2.5-32B-Instruct-20250208_093537
-tags:
-- generated_from_trainer
-- trl
-- sft
-licence: license
+pipeline_tag: text-generation
+inference: true
+license: apache-2.0
+datasets:
+- simplescaling/s1K-r1
 ---
 
-# Model Card for Qwen2.5-32B-Instruct-20250208_093537
+# Model Summary
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+> s1 is a reasoning model finetuned from Qwen2.5-32B-Instruct on just 1,000 examples. It matches o1-preview & exhibits test-time scaling via budget forcing.
 
-## Quick start
+- **Repository:** [simplescaling/s1](https://github.com/simplescaling/s1)
+- **Paper:** https://arxiv.org/abs/2501.19393
 
-```python
-from transformers import pipeline
+This model is a successor of [s1-32B](https://huggingface.co/simplescaling/s1-32B) with slightly better performance. Huge credits to [Ryan Marten](https://huggingface.co/ryanmarten) for helping assemble the dataset.
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="qfq/Qwen2.5-32B-Instruct-20250208_093537", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+# Use
 
-## Training procedure
+The model usage is documented [here](https://github.com/simplescaling/s1?tab=readme-ov-file#inference).
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/hashimoto-group/o1/runs/m1ilia77) 
-
-
-This model was trained with SFT.
-
-### Framework versions
-
-- TRL: 0.14.0
-- Transformers: 4.48.3
-- Pytorch: 2.3.1
-- Datasets: 3.0.1
-- Tokenizers: 0.21.0
-
-## Citations
-
-
-
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```