加载中...
加载中...
Qwen2.5-14B
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Qwen2.5-14B currently shows benchmark results led by MMLU Pro (90 / 114, score 63.69). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
阿里巴巴开源的千问大模型，是2.5代的140亿参数规模大语言模型。以Apache2.0开源协议开源，意味着可以完全免费商用，协议非常友好。
Qwen2.5-14B开源了多个不同的版本，包括基座版本和指令微调的版本：
| Qwen2.5-14B版本 | 版本简介 | HuggingFace开源地址 |
|---|---|---|
| Qwen2.5-14B | 320亿参数的基座模型 | https://huggingface.co/Qwen/Qwen2.5-14B |
| Qwen2.5-14B-Instruct | 指令微调版本 | https://huggingface.co/Qwen/Qwen2.5-14B-Instruct |
Qwen2.5-14B-Instruct-AWQ | AWQ的4bit量化版本的指令微调Qwen2.5 | https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-AWQ |
| Qwen2.5-14B-Instruct-GPTQ | GPTQ量化版本的指令微调Qwen2.5，包含不同的量化水平 | Int8： https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8 Int4： https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4 |
| Qwen2.5-14B-Instruct-GGUF | GGUF量化格式 | https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-GGUF |
欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送
