Instructions to use Qwen/Qwen2.5-VL-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2.5-VL-7B-Instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Qwen/Qwen2.5-VL-7B-Instruct")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
AMD Developer Cloud
Local Apps Settings

vLLM

How to use Qwen/Qwen2.5-VL-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2.5-VL-7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2.5-VL-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2.5-VL-7B-Instruct

SGLang

How to use Qwen/Qwen2.5-VL-7B-Instruct 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/Qwen2.5-VL-7B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2.5-VL-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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/Qwen2.5-VL-7B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2.5-VL-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2.5-VL-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2.5-VL-7B-Instruct
```

Batch Inference会报错

#19

by dingguofeng - opened Feb 11, 2025

Discussion

dingguofeng

Feb 11, 2025

Batch Inference会报错，ValueError: You are attempting to perform batched generation with padding_side='right' this may lead to unexpected behaviour for Flash Attention version of Qwen2_5_VL. Make sure to call tokenizer.padding_side = 'left' before tokenizing the input.
希望能修复一下
代码如下：
import os

import torch

os.environ["CUDA_VISIBLE_DEVICES"] = "6,7"
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
"/data/guofeng/test/DL/data/model/Qwen2.5-VL/Qwen2.5-VL-7B-Instruct",
torch_dtype = torch.bfloat16,
attn_implementation = "flash_attention_2",
device_map = "auto",
)

default processer

processor = AutoProcessor.from_pretrained("/data/guofeng/test/DL/data/model/Qwen2.5-VL/Qwen2.5-VL-7B-Instruct")

Sample messages for batch inference

messages1 = [
{
"role":"user",
"content":[
{"type":"image", "image":"/data/guofeng/test/image/skis.png"},
{"type":"image", "image":"/data/guofeng/test/image/soccer.jpg"},
{"type":"text", "text":"What are the common elements in these pictures?"},
],
}
]
messages2 = [
{"role":"system", "content":"You are a helpful assistant."},
{"role":"user", "content":"Who are you?"},
]

Combine messages for batch processing

messages = [messages1, messages2]

Preparation for batch inference

texts = [
processor.apply_chat_template(msg, tokenize = False, add_generation_prompt = True)
for msg in messages
]
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
text = texts,
images = image_inputs,
videos = video_inputs,
padding = True,
return_tensors = "pt",
)
inputs = inputs.to("cuda")

Batch Inference

generated_ids = model.generate(**inputs, max_new_tokens = 128)
generated_ids_trimmed = [
out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_texts = processor.batch_decode(
generated_ids_trimmed, skip_special_tokens = True, clean_up_tokenization_spaces = False
)
print(output_texts)

报错如下：
Loading checkpoint shards: 100%|██████████| 5/5 [00:03<00:00, 1.64it/s]
A decoder-only architecture is being used, but right-padding was detected! For correct generation results, please set padding_side='left' when initializing the tokenizer.
Traceback (most recent call last):
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/IPython/core/interactiveshell.py", line 3577, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 1, in
runfile('/data/guofeng/test/draft.py', args=['--gpu_name', '3090-3', '--cnt_parts', '4', '--current_part', '0', '--current_gpu', '0,1,2,3,4,5,6,7'], wdir='/data/guofeng/test/')
File "/data/guofeng/.pycharm_helpers/pydev/_pydev_bundle/pydev_umd.py", line 197, in runfile
pydev_imports.execfile(filename, global_vars, local_vars) # execute the script
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/guofeng/.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/data/guofeng/test/draft.py", line 53, in
generated_ids = model.generate(**inputs, max_new_tokens = 128)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/transformers/generation/utils.py", line 2228, in generate
result = self._sample(
^^^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/transformers/generation/utils.py", line 3211, in _sample
outputs = self(**model_inputs, return_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/accelerate/hooks.py", line 170, in new_forward
output = module._old_forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py", line 1808, in forward
outputs = self.model(
^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py", line 1124, in forward
causal_mask = self._update_causal_mask(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/guofeng/anaconda3/envs/4090-1/lib/python3.11/site-packages/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py", line 1203, in _update_causal_mask
raise ValueError(
ValueError: You are attempting to perform batched generation with padding_side='right' this may lead to unexpected behaviour for Flash Attention version of Qwen2_5_VL. Make sure to call tokenizer.padding_side = 'left' before tokenizing the input.

OBJECT-907

Feb 12, 2025

Add processor.padding_side="left"

dingguofeng

Feb 12, 2025

Add processor.padding_side="left"

This doesn’t work.

MickeyMouse2024

Feb 18, 2025

When I use the qwen2.5-0.5B-Instruct, I face the same problem: ValueError:.....with padding_side='right'.......Notice that I set tokenizer.padding_side='right' in my code . So I want you to check your tokenizer code

dingguofeng

Feb 18, 2025

Add processor.padding_side="left"

This doesn’t work.

processor.tokenizer.padding_side = "left"

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment