73 lines
2.2 KiB
Markdown
73 lines
2.2 KiB
Markdown
|
---
|
|||
|
|
license: llama3.2
|
|||
|
|
datasets:
|
|||
|
|
- OctoThinker/MegaMath-Web-Pro-Max
|
|||
|
|
- LLM360/MegaMath
|
|||
|
|
language:
|
|||
|
|
- en
|
|||
|
|
base_model:
|
|||
|
|
- meta-llama/Llama-3.2-3B
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# [OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling](https://arxiv.org/abs/2506.20512)
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
## OctoThinker-3B-Long-Zero
|
|||
|
|
|
|||
|
|
|
|||
|
|
The OctoThinker family is built on carefully studied mid-training insights, starting from the Llama-3 family, to create a reinforcement learning–friendly base language model.
|
|||
|
|
|
|||
|
|
OctoThinker-3B-Long-Zero is trained using the R1-Zero-style reinforcement learning technique, starting from OctoThinker-3B-Long-Base without any supervised fine-tuning (SFT).
|
|||
|
|
|
|||
|
|
|
|||
|
|
### Training Recipe for OctoThinker-3B-Long-Base
|
|||
|
|
|
|||
|
|
<div style="display: flex; justify-content: left; gap: 20px;">
|
|||
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/62cbeb2d72dfd24b86bdf977/fGkg_-5a2y8tI20025SOu.png" alt="Data Pipeline" style="width:90%;">
|
|||
|
|
</div>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
### Evaluation Results of OctoThinker-3B-Base Series
|
|||
|
|
|
|||
|
|
Note that we adopt the few-shot prompting evaluation for these base language models.
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div style="display: flex; justify-content: left; gap: 20px;">
|
|||
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/62cbeb2d72dfd24b86bdf977/UCZ9MahRYqLY0iKjiWMqS.png" alt="Data Pipeline" style="width:80%;">
|
|||
|
|
|
|||
|
|
</div>
|
|||
|
|
|
|||
|
|
|
|||
|
|
### RL Training Dynamics of OctoThinker-3B-Zero Series
|
|||
|
|
|
|||
|
|
<div style="display: flex; justify-content: left; gap: 20px;">
|
|||
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/62cbeb2d72dfd24b86bdf977/e21Eg8jj_ITxC4YcIJUmx.png" alt="Data Pipeline" style="width:80%;">
|
|||
|
|
</div>
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
### More about OctoThinker
|
|||
|
|
|
|||
|
|
|
|||
|
|
<div style="display: flex; justify-content: left; gap: 20px;">
|
|||
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/62cbeb2d72dfd24b86bdf977/bn85CEB_DW6azJ7KJp11Q.png" alt="Data Pipeline" style="width:100%;">
|
|||
|
|
</div>
|
|||
|
|
|
|||
|
|
|
|||
|
|
## Citation
|
|||
|
|
|
|||
|
|
Check out our [paper](https://arxiv.org/abs/2506.20512) for more details. If you use our models, datasets or find our work useful, please cite
|
|||
|
|
|
|||
|
|
```
|
|||
|
|
@article{wang2025octothinker,
|
|||
|
|
title={OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling},
|
|||
|
|
author={Wang, Zengzhi and Zhou, Fan and Li, Xuefeng and Liu, Pengfei},
|
|||
|
|
year={2025},
|
|||
|
|
journal={arXiv preprint arXiv:2506.20512},
|
|||
|
|
note={Preprint}
|
|||
|
|
}
|
|||
|
|
```
|