跳转到主要内容

Qwen2.5 7B Instruct

Alibaba Cloud / Qwen TeamQwenOpen WeightApache 2.0 · Commercial OK

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
33K
支持模态
text

能力雷达图

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

Science 在缺少专门科学评测时使用推理能力代理估算。

排行榜排名

暂无排名数据

基准测试分数 (LLM Stats)

Biology

GPQA36.4%自报

Code

HumanEval84.8%自报
LiveCodeBench28.7%自报

Communication

MT-Bench0.88 / 100自报

Creativity

AlignBench73.3%自报
Arena Hard52.0%自报

Finance

MMLU-Pro56.3%自报

General

MBPP0.79 / 100自报
MMLU-Redux75.4%自报
IFEval71.2%自报
MultiPL-E70.4%自报
LiveBench35.9%自报

Math

GSM8k91.6%自报
MATH75.5%自报

AA 评测指数

暂无 AA 评测数据

LLM Stats 分类评分

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

定价

输入价格$0.04 / 1M tokens
输出价格$0.1 / 1M tokens
混合价格(3:1)$0.055 / 1M tokens

速度

暂无速度数据

可用提供商

(LS 内部计价单位)

暂无提供商数据

外部链接