Instructions to use chaoyinshe/EchoVLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chaoyinshe/EchoVLM with Transformers:

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

pipe = pipeline("image-text-to-text", model="chaoyinshe/EchoVLM")
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, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("chaoyinshe/EchoVLM")
model = AutoModelForSeq2SeqLM.from_pretrained("chaoyinshe/EchoVLM")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use chaoyinshe/EchoVLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chaoyinshe/EchoVLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chaoyinshe/EchoVLM",
		"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/chaoyinshe/EchoVLM

SGLang

How to use chaoyinshe/EchoVLM 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 "chaoyinshe/EchoVLM" \
    --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": "chaoyinshe/EchoVLM",
		"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 "chaoyinshe/EchoVLM" \
        --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": "chaoyinshe/EchoVLM",
		"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 chaoyinshe/EchoVLM with Docker Model Runner:
```
docker model run hf.co/chaoyinshe/EchoVLM
```

ImportError: cannot import name 'Qwen2VLMOEForConditionalGeneration' from 'transformers'

by codecat777 - opened Dec 25, 2025

Discussion

codecat777

Dec 25, 2025

ImportError: cannot import name 'Qwen2VLMOEForConditionalGeneration' from 'transformers'

chaoyinshe

Owner Dec 26, 2025

This error occurs because Qwen2VLMOEForConditionalGeneration is not available in the official transformers library. If you haven't integrated this custom model into the transformers library source code, you should import it directly from your local module instead.
from EchoVLM import Qwen2VLMOEForConditionalGeneration

chaoyinshe

Owner Dec 26, 2025

ImportError: cannot import name 'Qwen2VLMOEForConditionalGeneration' from 'transformers'
Please see the latest pre-release of Echovlm V2 based on Lingshu. This version is based on qwen2.5vl, requires no code modifications, and is used exactly the same as qwen2.5vl. It also supports vLLM acceleration and performs better in clinical trials because this version uses a more rigorous data cleaning pipeline.

chaoyinshe changed discussion status to closed Dec 26, 2025

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