Instructions to use Qwen/Qwen-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen-VL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Qwen/Qwen-VL", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-VL", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Qwen/Qwen-VL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/Qwen-VL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Qwen/Qwen-VL
- SGLang
How to use Qwen/Qwen-VL with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Qwen/Qwen-VL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Qwen/Qwen-VL" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Qwen/Qwen-VL with Docker Model Runner:
docker model run hf.co/Qwen/Qwen-VL
Update README.md
#2
by eltociear - opened
README.md
CHANGED
|
@@ -58,7 +58,7 @@ For more details about Qwen-VL, please refer to our [technical memo](https://git
|
|
| 58 |
- Text-based VQA:评测模型对于图片中文字相关的识别/问答能力,例如文档问答、图表问答、文字问答等;
|
| 59 |
- Referring Expression Compression:评测模型给定物体描述画检测框的能力;
|
| 60 |
|
| 61 |
-
2. **试金石 (TouchStone)**:为了评测模型整体的图文对话能力和人类对齐水平。我们为此构建了一个基于 GPT4 打分来评测 LVLM 模型的 Benchmark:TouchStone。在 TouchStone-v0.1 中:
|
| 62 |
- 评测基准总计涵盖 300+张图片、800+道题目、27个类别。包括基础属性问答、人物地标问答、影视作品问答、视觉推理、反事实推理、诗歌创作、故事写作,商品比较、图片解题等**尽可能广泛的类别**。
|
| 63 |
- 为了弥补目前 GPT4 无法直接读取图片的缺陷,我们给所有的带评测图片提供了**人工标注的充分详细描述**,并且将图片的详细描述、问题和模型的输出结果一起交给 GPT4 打分。
|
| 64 |
- 评测同时包含英文版本和中文版本。
|
|
|
|
| 58 |
- Text-based VQA:评测模型对于图片中文字相关的识别/问答能力,例如文档问答、图表问答、文字问答等;
|
| 59 |
- Referring Expression Compression:评测模型给定物体描述画检测框的能力;
|
| 60 |
|
| 61 |
+
2. **试金石 (TouchStone)** :为了评测模型整体的图文对话能力和人类对齐水平。我们为此构建了一个基于 GPT4 打分来评测 LVLM 模型的 Benchmark:TouchStone。在 TouchStone-v0.1 中:
|
| 62 |
- 评测基准总计涵盖 300+张图片、800+道题目、27个类别。包括基础属性问答、人物地标问答、影视作品问答、视觉推理、反事实推理、诗歌创作、故事写作,商品比较、图片解题等**尽可能广泛的类别**。
|
| 63 |
- 为了弥补目前 GPT4 无法直接读取图片的缺陷,我们给所有的带评测图片提供了**人工标注的充分详细描述**,并且将图片的详细描述、问题和模型的输出结果一起交给 GPT4 打分。
|
| 64 |
- 评测同时包含英文版本和中文版本。
|