Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ pipeline_tag: text-generation
|
|
| 16 |
library_name: transformers
|
| 17 |
---
|
| 18 |
|
| 19 |
-
# FunReason-MT Technical Report:
|
| 20 |
|
| 21 |
[](https://arxiv.org/abs/2510.24645) [](https://huggingface.co/papers/2510.24645) [](https://huggingface.co/Bingguang/FunReason-MT) [](https://huggingface.co/datasets/Bingguang/FunReason-MT) [](https://github.com/inclusionAI/AWorld-RL) [](https://github.com/inclusionAI/AWorld)
|
| 22 |
|
|
@@ -42,7 +42,7 @@ The model was rigorously evaluated on the Berkeley Function-Calling Leaderboard
|
|
| 42 |
| Model (4B - 235B) | Multi-Turn (Overall) | Single-Turn (Overall) |
|
| 43 |
| :------------------------------------- | :------------------------------------------: | :------------------------------------------: |
|
| 44 |
| Qwen3-4B-Instruct (Base) | 15.75 | 78.19 |
|
| 45 |
-
| **Qwen3-4B + FunReason-MT (RL)** | **
|
| 46 |
| Claude-Sonnet-4-20250514 | 54.75 | 84.72 |
|
| 47 |
| DeepSeek-R1-0528 | 44.50 | 78.22 |
|
| 48 |
| GPT-4o-2024-11-20 | 42.50 | 77.21 |
|
|
@@ -233,8 +233,8 @@ If you use FunReason-MT in your research, please cite the technical report:
|
|
| 233 |
|
| 234 |
```
|
| 235 |
@article{xu2025funreason,
|
| 236 |
-
title={FunReason-MT Technical Report:
|
| 237 |
-
author={Zengzhuang Xu
|
| 238 |
journal={arXiv preprint arXiv:2510.24645},
|
| 239 |
year={2025}
|
| 240 |
}
|
|
|
|
| 16 |
library_name: transformers
|
| 17 |
---
|
| 18 |
|
| 19 |
+
# FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use
|
| 20 |
|
| 21 |
[](https://arxiv.org/abs/2510.24645) [](https://huggingface.co/papers/2510.24645) [](https://huggingface.co/Bingguang/FunReason-MT) [](https://huggingface.co/datasets/Bingguang/FunReason-MT) [](https://github.com/inclusionAI/AWorld-RL) [](https://github.com/inclusionAI/AWorld)
|
| 22 |
|
|
|
|
| 42 |
| Model (4B - 235B) | Multi-Turn (Overall) | Single-Turn (Overall) |
|
| 43 |
| :------------------------------------- | :------------------------------------------: | :------------------------------------------: |
|
| 44 |
| Qwen3-4B-Instruct (Base) | 15.75 | 78.19 |
|
| 45 |
+
| **Qwen3-4B + FunReason-MT (RL)** | **57.75** | **85.47** |
|
| 46 |
| Claude-Sonnet-4-20250514 | 54.75 | 84.72 |
|
| 47 |
| DeepSeek-R1-0528 | 44.50 | 78.22 |
|
| 48 |
| GPT-4o-2024-11-20 | 42.50 | 77.21 |
|
|
|
|
| 233 |
|
| 234 |
```
|
| 235 |
@article{xu2025funreason,
|
| 236 |
+
title={FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use},
|
| 237 |
+
author={Zengzhuang Xu, Bingguang Hao, Zechuan Wang, Yuntao Wen, Xinyi Xu, Yang Liu, Long Chen, Dong Wang, Maolin Wang, Tong Zhao, Yicheng Chen, Cunyin Peng, Jinjie Gu, Leilei Gan, Xiangyu Zhao, Chenyi Zhuang, Shi Gu},
|
| 238 |
journal={arXiv preprint arXiv:2510.24645},
|
| 239 |
year={2025}
|
| 240 |
}
|