Qwen-VL
Qwen-VL 是阿里云研发的大规模视觉语言模型（Large Vision Language Model, LVLM）。Qwen-VL 可以以图像、文本、检测框作为输入，并以文本和检测框作为输出。Qwen-VL 系列模型性能强大，具备多语言对话、多图交错对话等能力，并支持中文开放域定位和细粒度图像识别与理解。.
text → text · made by Alibaba
Sold by
Nobody in the catalogue publishes a price for this yet.
Measured 1 standing
| Place | Board | Metric | Score |
|---|---|---|---|
| 88thof 152 | LMArena · Vision | Score (Elo) (max) | 1185 |
About
Qwen-VL — a text model from Alibaba, placed 88th of 152 on LMArena · Vision.
It takes text and returns text, with a context window of 128,000 tokens. It was published in August 2023. Its sellers say it can call a tool. The catalogue files it under chat. It stands 88th of 152 on LMArena · Vision.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 128,000 tokens
- Longest answer
- 4,096 tokens
- Published
- August 2023
- Licence
- not read
- Boards
- 1
- Best place
- 88th of 152 — LMArena · Vision
Known as 1 name
Qwen/Qwen-VL