README.md

---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: OpenThinker2-7B
  results: []
datasets:
- open-thoughts/OpenThoughts2-1M
---

<p align="center">
    <img src="https://huggingface.co/datasets/open-thoughts/open-thoughts-114k/resolve/main/open_thoughts.png" width="50%">
</p>

# OpenThinker2-7B

This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the 
[OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset.

The [OpenThinker2-7B](https://huggingface.co/open-thoughts/OpenThinker2-7B) model is the top 7B open-data reasoning model. It delivers performance comparable to state of the art 7B models like [DeepSeek-R1-Distill-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) across a suite of tasks.
This model improves upon our previous [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) model, which was trained on 114k examples from [OpenThoughts-114k](https://huggingface.co/datasets/open-thoughts/open-thoughts-114k).
The numbers reported in the table below are evaluated with our open-source tool [Evalchemy](https://github.com/mlfoundations/Evalchemy).

| Model                                                                                         | Data | AIME24 | AIME25 | AMC23 | MATH500 | GPQA-D | LCBv2       |
| --------------------------------------------------------------------------------------------- | ---- | ------ | ------ | ----- | ------- | ------ | ----------- |
| [OpenThinker2-7B](https://huggingface.co/open-thoughts/OpenThinker2-7B)                       | ✅    | 50.0   | 33.3   | 89.5  | 88.4    | 49.3   | 55.6        |
| [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B)                         | ✅    | 31.3   | 23.3   | 74.5  | 83.2    | 42.9   | 38.0        |
| [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) | ❌    | 57.3   | 33.3   | 92.0  | 89.6    | 47.3   | 48.4        |
| [OlympicCoder-7B](https://huggingface.co/open-r1/OlympicCoder-7B)                             | ✅    | 20.7   | 15.3   | 63.0  | 74.8    | 25.3   | 55.4        |
| [OpenR1-Qwen-7B](https://huggingface.co/open-r1/OpenR1-Qwen-7B)                               | ✅    | 48.7   | 34.7   | 88.5  | 87.8    | 21.2   | 9.5<br><br> |

## Data

This model was trained on the [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset.

The [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset was constructed by augmenting [OpenThoughts-114k](https://huggingface.co/datasets/open-thoughts/open-thoughts-114k) with existing datasets like [OpenR1](https://huggingface.co/open-r1), as well as additional math and code reasoning data.
We generate the additional math and code data by ablating over 26 different question generation methodologies and sampling from the highest performing ones. 

See the [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset page or our [blog post](https://www.open-thoughts.ai/blog/thinkagain) for additional information.


## Intended uses & limitations

Apache 2.0 License


## Training procedure

We used 32 8xA100 nodes to train the model for 36 hours.

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 8e-05
- seed: 42
- distributed_type: multi-GPU
- num_devices: 256
- gradient_accumulation_steps: 2
- total_train_batch_size: 512
- 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: 5.0

### 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).

# Citation
```
@misc{openthoughts,
  author = {Team, OpenThoughts},
  month = jan,
  title = {{Open Thoughts}},
  howpublished = {https://open-thoughts.ai},
  year = {2025}
}
```

# Links
- 📊 [OpenThoughts2 and OpenThinker2 Blog Post](https://www.open-thoughts.ai/blog/thinkagain)
- 💻 [Open Thoughts GitHub Repository](https://github.com/open-thoughts/open-thoughts)
- 🧠 [OpenThoughts2-1M dataset](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M)
- 🤖 [OpenThinker2-7B model](https://huggingface.co/open-thoughts/OpenThinker2-7B) - this model.
- 🤖 [OpenThinker2-32B model](https://huggingface.co/open-thoughts/OpenThinker2-32B)