Update README.md

README.md

@@ -1,114 +1,59 @@
 ---
-base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets:
-- open-thoughts/OpenThoughts3-1.2M
+base_model:
+- open-thoughts/OpenThinker3-1.5B
 library_name: transformers
 license: apache-2.0
-tags:
-- llama-factory
-- full
-- generated_from_trainer
 model-index:
-- name: OpenThinker3-7B
+- name: OpenThinker3-1.5B-RLVE
   results: []
 pipeline_tag: text-generation
 ---
 
-<p align="center">
-    <img src="https://huggingface.co/datasets/open-thoughts/open-thoughts-114k/resolve/main/open_thoughts.png" width="50%">
-</p>
-
-<p align="center">
-<a href="https://arxiv.org/abs/2506.04178" style="margin-right: 24px;">paper</a> |
-<a href="https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M" style="margin-right: 24px; margin-left: 24px;">dataset</a> |
-<a href="https://huggingface.co/open-thoughts/OpenThinker3-7B" style="margin-left: 24px;">model</a>
-</p>
-
 > [!NOTE]
-> We have released a paper for OpenThoughts! See our paper [here](https://arxiv.org/abs/2506.04178).
+> For full information, go check out the RLVE paper [here](https://arxiv.org/abs/TODO).
 
-# OpenThinker3-1.5B
+# OpenThinker3 1.5B RLVE
 
-State-of-the-art SFT-only 1.5B reasoning model. 🚀
+OpenThinker 3 1.5B with additional RLVE training.
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the 
-[OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M) dataset. 
+This model is an RLVE-trained version of [Openthinker3 1.5B](https://huggingface.co/open-thoughts/OpenThinker3-1.5B) that has undergone RLVE training.
 
-See our [paper](https://arxiv.org/abs/2506.04178) and [blog post](https://openthoughts.ai/blog/ot3) for more details.
+See our [paper](https://arxiv.org/abs/TODO) for more details.
 
 # Evaluation Results
-The numbers reported in the table below are evaluated with our open-source tool [Evalchemy](https://github.com/mlfoundations/Evalchemy). 
-In the table below, we bold values in each column that are within 2 standard errors of the best.
-
-| Model                                                                                                        | AIME24 | AIME25 |  AMC23 | MATH500 | HMMT O2/25 | LCB 06/24-01/25 | CodeElo | CodeForces | GPQA-D | JEEBench |
-| ------------------------------------------------------------------------------------------------------------ | ------ | ------ | ------ | ------- | ---------- | --------------- | ------- | ---------- | ------ | -------- |
-| **[OpenThinker3-1.5B](https://huggingface.co/open-thoughts/OpenThinker3-1.5B)**                              |**52.0**|**41.7**|**87.0**|   86.4  | **27.3**   |  **39.4**       |  12.9   |  15.5      |  29.5  |  51.9    |
-| [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B)            |  32.3  |  23.7  |  71.8  |   80.8  |   15.3     |    27.2         |  8.8    |  8.5       |  31.1  |  32.5    |
-| [Nemotron-Research-Reasoning-Qwen-1.5B](https://huggingface.co/nvidia/Nemotron-Research-Reasoning-Qwen-1.5B) |**47.7**|  32.0  |**87.5**|   86.0  |   21.7     |    31.4         |**54.7** |**40.3**    |  41.8  |  52.6    |
-| [Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B)                                                         |**52.0**|  35.3  |  83.8  | **87.2**|   23.3     |    27.7         |  20.7   |  20.0      |**49.3**|**60.7**  |
-| [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)                                   |  3.0   |  0.7   |  30.8  |   50.2  |   0.0      |    5.5          |  0.8    |   2.2      |  24.7  |  16.4    |
-
-# Data
-
-This model was trained on the [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M) dataset.
-
-The key to the strong model performance is our comprehensive data pipeline and over 1,000+ ablation experiments.
-This led to the creation of [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M), which consists of 850,000 math questions, 250,000 code questions, and 100,000 science questions.
-Reasoning traces are generated with QwQ-32B. 
 
-See the [OpenThoughts3-1.2M](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M) dataset page or our [paper](https://arxiv.org/abs/2506.04178) for additional information.
 
+| Benchmark | AIME 2024 (Avg@64) | AIME 2025 (Avg@64) | OMEGA-500 (Avg@4) | OlympiadBench (Avg@4) | BBEH (Avg@4) | LiveCodeBench-v6 (Pass@8) |
+|:-----------|:------------------:|:------------------:|:-----------------:|:----------------------:|:-------------:|:--------------------------:|
+| [OpenThinker3-1.5B](https://huggingface.co/open-thoughts/OpenThinker3-1.5B) | 54.32 | 42.03 | 25.15 | 56.85 | 4.00 | 28.17 |
+| [OpenThinker3-1.5B-RLVE](https://huggingface.co/hamishivi/OpenThinker3-1.5B-RLVE) | **58.18** | **49.90** | **29.45** | **62.67** | **7.13** | **34.07** |
 
 # Intended uses & limitations
 
 Apache 2.0 License
 
-## Training procedure
+## Training
 
-We used 64 A100 gpus to train the model for 7 days.
+For training details and hyperparameters. please see [our repository](https://github.com/Zhiyuan-Zeng/RLVE).
 
-## Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 0.00016
-- train_batch_size: 4
-- eval_batch_size: 8
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 64
-- total_train_batch_size: 256
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 7.0
-
-## Framework versions
-
-- Transformers 4.46.1
-- Pytorch 2.3.0
-- Datasets 3.1.0
-- Tokenizers 0.20.3
-
-More info can be found in our repository: [https://github.com/open-thoughts/open-thoughts](https://github.com/open-thoughts/open-thoughts).
+In particular, you can rerun training for this model with this command (after setting up the repository):
+```bash
+bash scripts/training/OpenThinker3-1.5B/rlve/num-environment=400.sh RLVE
+```
 
 # Links
-- 📝 [OpenThoughts Paper](https://arxiv.org/abs/2506.04178)
-- 📊 [OpenThoughts3-1.2M and OpenThinker3-7B Blog Post](https://www.open-thoughts.ai/blog/ot3)
-- 💻 [Open Thoughts GitHub Repository](https://github.com/open-thoughts/open-thoughts)
-- 🧠 [OpenThoughts3-1.2M dataset](https://huggingface.co/datasets/open-thoughts/OpenThoughts3-1.2M)
-- 🤖 [OpenThinker3-7B model](https://huggingface.co/open-thoughts/OpenThinker3-7B)
-- 🤖 [OpenThinker3-1.5B model](https://huggingface.co/open-thoughts/OpenThinker3-1.5B) - this model.
+- 📝 [RLVE Paper](https://arxiv.org/abs/TODO)
+- 💻 [RLVE GitHub Repository](https://github.com/Zhiyuan-Zeng/RLVE)
+- 🤖 [Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE](https://huggingface.co/hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE)
+- 🤖 [OpenThinker3-1.5B-RLVE](https://huggingface.co/hamishivi/OpenThinker3-1.5B-RLVE) - this model.
 
 
 # Citation
 ```
-@misc{guha2025openthoughtsdatarecipesreasoning,
-  title={OpenThoughts: Data Recipes for Reasoning Models}, 
-  author={Etash Guha and Ryan Marten and Sedrick Keh and Negin Raoof and Georgios Smyrnis and Hritik Bansal and Marianna Nezhurina and Jean Mercat and Trung Vu and Zayne Sprague and Ashima Suvarna and Benjamin Feuer and Liangyu Chen and Zaid Khan and Eric Frankel and Sachin Grover and Caroline Choi and Niklas Muennighoff and Shiye Su and Wanjia Zhao and John Yang and Shreyas Pimpalgaonkar and Kartik Sharma and Charlie Cheng-Jie Ji and Yichuan Deng and Sarah Pratt and Vivek Ramanujan and Jon Saad-Falcon and Jeffrey Li and Achal Dave and Alon Albalak and Kushal Arora and Blake Wulfe and Chinmay Hegde and Greg Durrett and Sewoong Oh and Mohit Bansal and Saadia Gabriel and Aditya Grover and Kai-Wei Chang and Vaishaal Shankar and Aaron Gokaslan and Mike A. Merrill and Tatsunori Hashimoto and Yejin Choi and Jenia Jitsev and Reinhard Heckel and Maheswaran Sathiamoorthy and Alexandros G. Dimakis and Ludwig Schmidt},
-  year={2025},
-  eprint={2506.04178},
-  archivePrefix={arXiv},
-  primaryClass={cs.LG},
-  url={https://arxiv.org/abs/2506.04178}, 
+@article{zeng2025rlve,
+  title={RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments},
+  author={Zeng, Zhiyuan and Ivison, Hamish and Wang, Yiping and Yuan, Lifan and Li, Shuyue Stella and Ye, Zhuorui and Li, Siting and He, Jacqueline and Zhou, Runlong and Chen, Tong and Zhao, Chenyang and Tsvetkov, Yulia and Du, Simon Shaolei and Jaques, Natasha and Peng, Hao and Koh, Pang Wei and Hajishirzi, Hannaneh},
+  journal={[TODO ARXIV]},
+  year={2025}
 }
 ```