82 lines
3.2 KiB
Markdown
82 lines
3.2 KiB
Markdown
---
|
||
library_name: transformers
|
||
base_model: Qwen/Qwen3-8B-Base
|
||
tags:
|
||
- multilingual
|
||
- reasoning
|
||
- LLM
|
||
- qwen3
|
||
license: apache-2.0
|
||
datasets:
|
||
- lightonai/Dolci-Think-SFT-32B-Multilingual
|
||
language:
|
||
- en
|
||
pipeline_tag: text-generation
|
||
---
|
||
|
||
# Qwen3-8B-EN
|
||
|
||
`Qwen3-8B-EN` is a **native reasoning model** fine-tuned from [`Qwen/Qwen3-8B-Base`](https://huggingface.co/Qwen/Qwen3-8B-Base) to reason in English. This model produces its **entire reasoning trace in English** before delivering the final answer in English.
|
||
|
||
It is released alongside the paper [**Rethinking the Multilingual Reasoning Gap with Layer Swap**](https://arxiv.org/abs/2605.26735).
|
||
|
||
## Model details
|
||
|
||
- **Base model:** `Qwen/Qwen3-8B-Base`
|
||
- **Language:** English (CoT and answer)
|
||
- **Training:** Full SFT, ~10B tokens, 2 epochs
|
||
- **Context length:** 32,768 tokens
|
||
- **Dataset:** [`lightonai/Dolci-Think-SFT-32B-Multilingual`](https://huggingface.co/datasets/lightonai/Dolci-Think-SFT-32B-Multilingual) (English split).
|
||
|
||
> [!NOTE]
|
||
> The model was trained on data derived from `allenai/Dolci-Think-SFT-32B`, released under the ODC-BY-1.0 license.
|
||
|
||
## Evaluation
|
||
|
||
All scores are mean accuracy (%) on the **English** version of each benchmark, with sample standard deviation across runs. AIME 24/25 is averaged over 30 runs; the others over 10 runs, using the recommended generation parameters.
|
||
|
||
| Model | MGSM-Rev2 | Global-MMLU-Lite | GPQA-Diamond | AIME 24/25 | HumanEvalPlus | Average |
|
||
|---|:---:|:---:|:---:|:---:|:---:|:---:|
|
||
| `Qwen3-8B-EN` | 98.96 | 81.72 | 55.66 | 62.89 | 85.75 | 77.00 |
|
||
|
||
**Benchmarks used:**
|
||
|
||
- [`lightonai/gpqa_diamond_multilingual`](https://huggingface.co/datasets/lightonai/gpqa_diamond_multilingual)
|
||
- [`lightonai/aime24_multilingual`](https://huggingface.co/datasets/lightonai/aime24_multilingual)
|
||
- [`lightonai/aime25_multilingual`](https://huggingface.co/datasets/lightonai/aime25_multilingual)
|
||
- [`lightonai/HumanEvalPlus_multilingual`](https://huggingface.co/datasets/lightonai/HumanEvalPlus_multilingual)
|
||
- [`lightonai/mgsm-rev2`](https://huggingface.co/datasets/lightonai/mgsm-rev2)
|
||
- [`CohereLabs/Global-MMLU-Lite`](https://huggingface.co/datasets/CohereLabs/Global-MMLU-Lite)
|
||
|
||
## Usage
|
||
|
||
```python
|
||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
||
model_name = "lightonai/Qwen3-8B-EN"
|
||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
|
||
|
||
messages = [{"role": "user", "content": "Solve: 24 × 17 = ?"}]
|
||
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
|
||
|
||
outputs = model.generate(inputs, max_new_tokens=32768, temperature=1.0, top_p=0.95, top_k=20)
|
||
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
|
||
```
|
||
|
||
Recommended sampling: `temperature=1.0`, `top_p=0.95`, `top_k=20`, `min_p=0`.
|
||
|
||
## Citation
|
||
|
||
If you find our work helpful, feel free to give us a cite.
|
||
|
||
```bibtex
|
||
@misc{lasbordes2026rethinking,
|
||
title = {Rethinking the Multilingual Reasoning Gap with Layer Swap},
|
||
author = {Lasbordes, Maxence and Chatelain, Amélie and Seddah, Djamé},
|
||
year = {2026},
|
||
eprint = {2605.26735},
|
||
archivePrefix= {arXiv},
|
||
primaryClass = {cs.CL}
|
||
}
|
||
``` |