Qwen2.5 7B Instruct
Qwen/Qwen2.5-7B-Instruct
Open Source · chat · open-weights
Open
Alert me on changes
Context
32.8K
Max output
8.2K
Weights
Open
API $/1M
$0.10 / $0.20
Modalities
text
Released
16 Sept 2024
License: apache-2.0 · Qwen/Qwen2.5-7B-Instruct
AI summary
● machine-written
Qwen2.5 7B Instruct: 7B open-weights chat model with 32K context
Qwen2.5 7B Instruct is a 7-billion-parameter open-source instruction-tuned language model from Alibaba Cloud released October 2024. The model supports a 32,768-token context window with improvements in coding, mathematics, instruction following, and long-text generation up to 8K tokens. It is available open-weights under Apache 2.0 license with API access through multiple providers.
What's new
- Released October 16, 2024
- Supports long-context up to 128K tokens and can generate up to 8K tokens
- Improved capabilities in coding, mathematics, and structured data understanding
- Multilingual support for 29+ languages
- Tool calling and structured output features available
Best for
Long-form text generation and summarizationCode-related tasks and mathematical problem solvingInstruction following and role-play scenariosStructured data processing and JSON generation