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

Libraries

How to use unsloth/Qwen2-VL-7B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="unsloth/Qwen2-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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("unsloth/Qwen2-VL-7B-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("unsloth/Qwen2-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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unsloth/Qwen2-VL-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen2-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": "unsloth/Qwen2-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/unsloth/Qwen2-VL-7B-Instruct

SGLang

How to use unsloth/Qwen2-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 "unsloth/Qwen2-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": "unsloth/Qwen2-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 "unsloth/Qwen2-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": "unsloth/Qwen2-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"
						}
					}
				]
			}
		]
	}'

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

danielhanchen commited on Mar 9, 2025

Commit

710e475

verified ·

1 Parent(s): 2ebce44

Add files using upload-large-folder tool

Browse files

Files changed (10) hide show

config.json +3 -3
generation_config.json +1 -1
model-00001-of-00005.safetensors +3 -0
model-00002-of-00005.safetensors +3 -0
model-00003-of-00005.safetensors +3 -0
model-00004-of-00005.safetensors +3 -0
model-00005-of-00005.safetensors +3 -0
model.safetensors.index.json +0 -0
preprocessor_config.json +2 -2
tokenizer_config.json +1 -0

@@ -4,7 +4,6 @@
     "Qwen2VLForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 3584,
@@ -32,7 +31,7 @@
   "sliding_window": 32768,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
   "unsloth_fixed": true,
   "use_cache": true,
   "use_sliding_window": false,
@@ -40,7 +39,8 @@
   "vision_config": {
     "in_chans": 3,
     "model_type": "qwen2_vl",
-    "spatial_patch_size": 14
   },
   "vision_end_token_id": 151653,
   "vision_start_token_id": 151652,

     "Qwen2VLForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 3584,
   "sliding_window": 32768,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
   "unsloth_fixed": true,
   "use_cache": true,
   "use_sliding_window": false,
   "vision_config": {
     "in_chans": 3,
     "model_type": "qwen2_vl",
+    "spatial_patch_size": 14,
+    "torch_dtype": "bfloat16"
   },
   "vision_end_token_id": 151653,
   "vision_start_token_id": 151652,

@@ -10,5 +10,5 @@
   "temperature": 0.01,
   "top_k": 1,
   "top_p": 0.001,
-  "transformers_version": "4.46.3"
 }

   "temperature": 0.01,
   "top_k": 1,
   "top_p": 0.001,
+  "transformers_version": "4.49.0"
 }

@@ -22,8 +22,8 @@
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "max_pixels": 12845056,
-    "min_pixels": 3136
   },
   "temporal_patch_size": 2
 }

+version https://git-lfs.github.com/spec/v1
+oid sha256:eab4f4dc1abf860794c98ce3759b4ace1059fc0fc041ede76b88988b3557c132
+size 3898649896

+version https://git-lfs.github.com/spec/v1
+oid sha256:0546b7cd070ff239de0f61a28770de6a0ac517ad313071e151653e38911ffb25
+size 3864726320

+version https://git-lfs.github.com/spec/v1
+oid sha256:11368ea1e9c0039ca54012a74ac32d543a9e9d980b2d0ad7e93af0341ace1fe6
+size 3864726424

+version https://git-lfs.github.com/spec/v1
+oid sha256:381e110d74db594cc24956af0e74a01ae02104497113a78926990c5bd1f395f6
+size 3864733680

+version https://git-lfs.github.com/spec/v1
+oid sha256:e76ec4dc2e7c0dcbe3432e58fae08e62204a2ef2323069d85c8fa0affb87332a
+size 1089994880

@@ -134,6 +134,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "model_max_length": 32768,
   "pad_token": "<|vision_pad|>",
   "padding_side": "left",

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@