Instructions to use trl-internal-testing/tiny-Qwen2VLForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-Qwen2VLForConditionalGeneration with Transformers:

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

pipe = pipeline("image-text-to-text", model="trl-internal-testing/tiny-Qwen2VLForConditionalGeneration")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("trl-internal-testing/tiny-Qwen2VLForConditionalGeneration")
model = AutoModelForImageTextToText.from_pretrained("trl-internal-testing/tiny-Qwen2VLForConditionalGeneration")
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 trl-internal-testing/tiny-Qwen2VLForConditionalGeneration with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-Qwen2VLForConditionalGeneration"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-Qwen2VLForConditionalGeneration",
		"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/trl-internal-testing/tiny-Qwen2VLForConditionalGeneration

SGLang

How to use trl-internal-testing/tiny-Qwen2VLForConditionalGeneration 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 "trl-internal-testing/tiny-Qwen2VLForConditionalGeneration" \
    --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": "trl-internal-testing/tiny-Qwen2VLForConditionalGeneration",
		"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 "trl-internal-testing/tiny-Qwen2VLForConditionalGeneration" \
        --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": "trl-internal-testing/tiny-Qwen2VLForConditionalGeneration",
		"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 trl-internal-testing/tiny-Qwen2VLForConditionalGeneration with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-Qwen2VLForConditionalGeneration
```

Upload Qwen2VLForConditionalGeneration

by albertvillanova HF Staff - opened Jan 15

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

-4

Files changed (3) hide show

config.json +1 -2
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -30,7 +30,6 @@
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "text_config": {
-    "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
     "architectures": [
       "Qwen2VLForConditionalGeneration"
     ],
@@ -69,7 +68,7 @@
     "vision_token_id": 151654,
     "vocab_size": 151936
   },
-  "transformers_version": "4.57.3",
   "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,

   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "text_config": {
     "architectures": [
       "Qwen2VLForConditionalGeneration"
     ],
     "vision_token_id": 151654,
     "vocab_size": 151936
   },
+  "transformers_version": "4.57.5",
   "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,

generation_config.json CHANGED Viewed

@@ -9,5 +9,5 @@
   "temperature": 0.01,
   "top_k": 1,
   "top_p": 0.001,
-  "transformers_version": "4.57.3"
 }

   "temperature": 0.01,
   "top_k": 1,
   "top_p": 0.001,
+  "transformers_version": "4.57.5"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa795ef6b498f4a77fc3bcc4ada0a56518ec769ca4ad7f42c75c778d86731a4
 size 7081872

 version https://git-lfs.github.com/spec/v1
+oid sha256:b17688b7042bd32913d5970b53043b8481f071e73ab15e4da04895eb80930c3e
 size 7081872