taobao-mnn / Qwen3-4B-Thinking-2507-Eagle

huggingface.co
Total runs: 60
24-hour runs: 0
7-day runs: 0
30-day runs: 53
Model's Last Updated: November 10 2025
text-generation

Introduction of Qwen3-4B-Thinking-2507-Eagle

Model Details of Qwen3-4B-Thinking-2507-Eagle

EAGLE-3 Draft Model for Qwen3-4B-Thinking-2507

Model Overview

This repository contains an EAGLE-3 style draft model specifically trained to accelerate the inference of the Qwen3-4B-Thinking-2507 large language model.

This is not a standalone model . It must be used in conjunction with its corresponding base model ( Qwen3-4B-Thinking-2507 ) within a speculative decoding framework to achieve significant speedups in text generation.

  • Base Model: Qwen3-4B-Thinking-2507
  • Model Architecture: EAGLE-3 (Speculative Decoding Draft Model)
  • Primary Benefit: Accelerates text generation throughput by 1.5x to 2.5x without compromising the generation quality of the base model.
What is EAGLE?

EAGLE (Extrapolative A* Generative Language Engine) is an advanced speculative decoding method. It uses a small draft model to generate a sequence of draft tokens in parallel. These tokens are then verified by the larger, more powerful base model in a single forward pass. If the draft is accepted, the generation process advances multiple steps at once, leading to a substantial increase in speed.

Performance

This model was evaluated on a diverse set of benchmarks. The acc_length (average number of accepted draft tokens) indicates the efficiency of the acceleration. A higher value is better.

Benchmark acc_length (num_draft_tokens=4) acc_length (num_draft_tokens=8)
gsm8k 2.07 2.07
humaneval 1.99 1.98
math500 1.98 1.98
ceval 1.82 1.82
cmmlu 1.76 1.76
mtbench 1.71 1.71
Average ~1.89 ~1.89

These results demonstrate consistent and effective acceleration across various tasks, including coding, math, and general conversation.

Training Details
  • Training Framework: This model was trained using SpecForge , an open-source framework for speculative decoding research.
  • Training Data: The model was trained on the EagleChat dataset. Available on Hugging Face and ModelScope .

适用于 Qwen3-4B-Thinking-2507 的 EAGLE-3 草稿模型

模型简介

本仓库包含一个 EAGLE-3 风格的草稿模型 ,专为加速 Qwen3-4B-Thinking-2507 大语言模型的推理而训练。

请注意:这是一个 非独立模型 。它必须与对应的基座模型 ( Qwen3-4B-Thinking-2507 ) 在推测解码 (speculative decoding) 框架下配合使用,才能实现显著的文本生成加速效果。

  • 基座模型: Qwen3-4B-Thinking-2507
  • 模型架构: EAGLE-3 (推测解码草稿模型)
  • 核心优势: 在不牺牲基座模型生成质量的前提下,将文本生成吞吐量提升 1.5 到 2.5 倍。
什么是 EAGLE?

EAGLE (Extrapolative A* Generative Language Engine) 是一种先进的推测解码方法。它利用一个轻量的草稿模型并行生成一系列草稿词元 (draft tokens),然后由更大、更强的基座模型通过单次前向传播进行验证。如果草稿被接受,生成过程就能一次性前进多个步骤,从而实现显著的速度提升。

性能表现

本模型在一系列多样化的评测基准上进行了评估。 acc_length (平均接受的草稿词元数) 反映了加速的效率,数值越高越好。

评测基准 (Benchmark) acc_length (num_draft_tokens=4) acc_length (num_draft_tokens=8)
gsm8k 2.07 2.07
humaneval 1.99 1.98
math500 1.98 1.98
ceval 1.82 1.82
cmmlu 1.76 1.76
mtbench 1.71 1.71
平均值 ~1.89 ~1.89

这些结果表明,该模型在编码、数学和通用对话等不同任务上都能提供稳定且高效的加速效果。

训练细节
  • 训练框架: 本模型使用开源推测解码研究框架 SpecForge 进行训练。
  • 训练数据: 训练数据使用了 EagleChat 数据集。您可以在 Hugging Face 或 ModelScope 上获取该数据集。

Runs of taobao-mnn Qwen3-4B-Thinking-2507-Eagle on huggingface.co

60
Total runs
0
24-hour runs
3
3-day runs
0
7-day runs
53
30-day runs

More Information About Qwen3-4B-Thinking-2507-Eagle huggingface.co Model

More Qwen3-4B-Thinking-2507-Eagle license Visit here:

https://choosealicense.com/licenses/apache-2.0

Qwen3-4B-Thinking-2507-Eagle huggingface.co

Qwen3-4B-Thinking-2507-Eagle huggingface.co is an AI model on huggingface.co that provides Qwen3-4B-Thinking-2507-Eagle's model effect (), which can be used instantly with this taobao-mnn Qwen3-4B-Thinking-2507-Eagle model. huggingface.co supports a free trial of the Qwen3-4B-Thinking-2507-Eagle model, and also provides paid use of the Qwen3-4B-Thinking-2507-Eagle. Support call Qwen3-4B-Thinking-2507-Eagle model through api, including Node.js, Python, http.

Qwen3-4B-Thinking-2507-Eagle huggingface.co Url

https://huggingface.co/taobao-mnn/Qwen3-4B-Thinking-2507-Eagle

taobao-mnn Qwen3-4B-Thinking-2507-Eagle online free

Qwen3-4B-Thinking-2507-Eagle huggingface.co is an online trial and call api platform, which integrates Qwen3-4B-Thinking-2507-Eagle's modeling effects, including api services, and provides a free online trial of Qwen3-4B-Thinking-2507-Eagle, you can try Qwen3-4B-Thinking-2507-Eagle online for free by clicking the link below.

taobao-mnn Qwen3-4B-Thinking-2507-Eagle online free url in huggingface.co:

https://huggingface.co/taobao-mnn/Qwen3-4B-Thinking-2507-Eagle

Qwen3-4B-Thinking-2507-Eagle install

Qwen3-4B-Thinking-2507-Eagle is an open source model from GitHub that offers a free installation service, and any user can find Qwen3-4B-Thinking-2507-Eagle on GitHub to install. At the same time, huggingface.co provides the effect of Qwen3-4B-Thinking-2507-Eagle install, users can directly use Qwen3-4B-Thinking-2507-Eagle installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Qwen3-4B-Thinking-2507-Eagle install url in huggingface.co:

https://huggingface.co/taobao-mnn/Qwen3-4B-Thinking-2507-Eagle

Url of Qwen3-4B-Thinking-2507-Eagle

Qwen3-4B-Thinking-2507-Eagle huggingface.co Url

Provider of Qwen3-4B-Thinking-2507-Eagle huggingface.co

taobao-mnn
ORGANIZATIONS

Other API from taobao-mnn

huggingface.co

Total runs: 95
Run Growth: 18
Growth Rate: 18.95%
Updated:December 31 2024