跳转到主要内容

Qwen2.5 7B Instruct

Alibaba Cloud / Qwen TeamQwen开源权重Apache 2.0 · 商用许可

描述

Qwen2.5-7B-Instruct is an instruction-tuned 7B parameter language model that excels at following instructions, generating long texts (over 8K tokens), understanding structured data, and generating structured outputs like JSON. The model features enhanced capabilities in mathematics, coding, and multilingual support across 29+ languages including Chinese, English, French, Spanish, and more.

发布日期
2024-09-19
参数规模
7.6B
上下文长度
—
支持模态
text

能力雷达图

70
general
60
coding
70
reasoning
34
science估算
67
agents
0
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

暂无排名数据

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Chat

MT-Bench0.88 / 100自报
IFEvalGoogle Research (2023)71.2%自报

General

AlignBench73.3%自报
MultiPL-E70.4%自报
Arena Hard52.0%自报

Language

MMLU-Redux75.4%自报
MMLU-Pro56.3%自报

Math

GSM8k91.6%自报
MATH75.5%自报
LiveBench35.9%自报

Reasoning

HumanEvalOpenAI (2021)84.8%自报
MBPP0.79 / 100自报
GPQANYU + Cohere + Anthropic (2023)36.4%自报
LiveCodeBench28.7%自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Communication
90
Roleplay
80
Chat
70
Instruction Following
70
Language
70
Math
70
Structured Output
70
General
70
Creativity
70
Legal
60
Reasoning
60
Finance
60
Healthcare
60
Code
60
Writing
60
Physics
40
Biology
40
Chemistry
40

定价

暂无定价数据

速度

暂无速度数据

供应商价格排行

暂无提供商数据

外部链接