Instructions to use LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start with Transformers:

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

pipe = pipeline("image-text-to-text", model="LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start")
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("LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start")
model = AutoModelForImageTextToText.from_pretrained("LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start")
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 LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start",
		"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/LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start

SGLang

How to use LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start 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 "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start" \
    --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": "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start",
		"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 "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start" \
        --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": "LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start",
		"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 LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start with Docker Model Runner:
```
docker model run hf.co/LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start
```

Qwen-2.5VL-3B-Cold-Start / trainer_log.jsonl

zli12321

Upload folder using huggingface_hub

ddbac2f verified 9 months ago

raw

history blame contribute delete

3.39 kB

	{"current_steps": 10, "total_steps": 177, "loss": 0.8834, "lr": 5.555555555555557e-06, "epoch": 0.16806722689075632, "percentage": 5.65, "elapsed_time": "0:01:07", "remaining_time": "0:18:45"}
	{"current_steps": 20, "total_steps": 177, "loss": 0.832, "lr": 9.99609654676786e-06, "epoch": 0.33613445378151263, "percentage": 11.3, "elapsed_time": "0:02:15", "remaining_time": "0:17:41"}
	{"current_steps": 30, "total_steps": 177, "loss": 0.7929, "lr": 9.860114570402055e-06, "epoch": 0.5042016806722689, "percentage": 16.95, "elapsed_time": "0:03:19", "remaining_time": "0:16:19"}
	{"current_steps": 40, "total_steps": 177, "loss": 0.7613, "lr": 9.535012074008688e-06, "epoch": 0.6722689075630253, "percentage": 22.6, "elapsed_time": "0:04:18", "remaining_time": "0:14:46"}
	{"current_steps": 50, "total_steps": 177, "loss": 0.7369, "lr": 9.033439696227966e-06, "epoch": 0.8403361344537815, "percentage": 28.25, "elapsed_time": "0:05:20", "remaining_time": "0:13:33"}
	{"current_steps": 60, "total_steps": 177, "loss": 0.6853, "lr": 8.374915007591053e-06, "epoch": 1.0, "percentage": 33.9, "elapsed_time": "0:06:18", "remaining_time": "0:12:17"}
	{"current_steps": 70, "total_steps": 177, "loss": 0.6288, "lr": 7.58506302778873e-06, "epoch": 1.1680672268907564, "percentage": 39.55, "elapsed_time": "0:07:23", "remaining_time": "0:11:17"}
	{"current_steps": 80, "total_steps": 177, "loss": 0.5971, "lr": 6.694619085176159e-06, "epoch": 1.3361344537815127, "percentage": 45.2, "elapsed_time": "0:08:21", "remaining_time": "0:10:07"}
	{"current_steps": 90, "total_steps": 177, "loss": 0.5633, "lr": 5.738232820012407e-06, "epoch": 1.504201680672269, "percentage": 50.85, "elapsed_time": "0:09:27", "remaining_time": "0:09:08"}
	{"current_steps": 100, "total_steps": 177, "loss": 0.5586, "lr": 4.753119870981486e-06, "epoch": 1.6722689075630253, "percentage": 56.5, "elapsed_time": "0:10:28", "remaining_time": "0:08:04"}
	{"current_steps": 110, "total_steps": 177, "loss": 0.5633, "lr": 3.777613711607087e-06, "epoch": 1.8403361344537816, "percentage": 62.15, "elapsed_time": "0:11:30", "remaining_time": "0:07:00"}
	{"current_steps": 120, "total_steps": 177, "loss": 0.5249, "lr": 2.8496739886173994e-06, "epoch": 2.0, "percentage": 67.8, "elapsed_time": "0:12:30", "remaining_time": "0:05:56"}
	{"current_steps": 130, "total_steps": 177, "loss": 0.4774, "lr": 2.005409406946e-06, "epoch": 2.168067226890756, "percentage": 73.45, "elapsed_time": "0:13:35", "remaining_time": "0:04:54"}
	{"current_steps": 140, "total_steps": 177, "loss": 0.4569, "lr": 1.277672640004936e-06, "epoch": 2.3361344537815127, "percentage": 79.1, "elapsed_time": "0:14:38", "remaining_time": "0:03:52"}
	{"current_steps": 150, "total_steps": 177, "loss": 0.4598, "lr": 6.947819411632223e-07, "epoch": 2.504201680672269, "percentage": 84.75, "elapsed_time": "0:15:41", "remaining_time": "0:02:49"}
	{"current_steps": 160, "total_steps": 177, "loss": 0.4533, "lr": 2.7941920206915443e-07, "epoch": 2.6722689075630255, "percentage": 90.4, "elapsed_time": "0:16:44", "remaining_time": "0:01:46"}
	{"current_steps": 170, "total_steps": 177, "loss": 0.4608, "lr": 4.774733741942206e-08, "epoch": 2.8403361344537816, "percentage": 96.05, "elapsed_time": "0:17:48", "remaining_time": "0:00:43"}
	{"current_steps": 177, "total_steps": 177, "epoch": 2.957983193277311, "percentage": 100.0, "elapsed_time": "0:18:55", "remaining_time": "0:00:00"}