Instructions to use XiXiHaHaZhao/STAGE2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XiXiHaHaZhao/STAGE2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="XiXiHaHaZhao/STAGE2")
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("XiXiHaHaZhao/STAGE2")
model = AutoModelForMultimodalLM.from_pretrained("XiXiHaHaZhao/STAGE2", 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 XiXiHaHaZhao/STAGE2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XiXiHaHaZhao/STAGE2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XiXiHaHaZhao/STAGE2",
		"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/XiXiHaHaZhao/STAGE2

SGLang

How to use XiXiHaHaZhao/STAGE2 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 "XiXiHaHaZhao/STAGE2" \
    --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": "XiXiHaHaZhao/STAGE2",
		"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 "XiXiHaHaZhao/STAGE2" \
        --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": "XiXiHaHaZhao/STAGE2",
		"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 XiXiHaHaZhao/STAGE2 with Docker Model Runner:
```
docker model run hf.co/XiXiHaHaZhao/STAGE2
```

STAGE2 / trainer_log.jsonl

XiXiHaHaZhao

upload model

eae765c verified about 2 months ago

Raw History Blame Contribute Delete

4.02 kB

{"current_steps": 10, "total_steps": 192, "loss": 0.408135986328125, "lr": 4.5e-06, "epoch": 0.1568627450980392, "percentage": 5.21, "elapsed_time": "0:01:53", "remaining_time": "0:34:30"}
{"current_steps": 20, "total_steps": 192, "loss": 0.23105964660644532, "lr": 9.5e-06, "epoch": 0.3137254901960784, "percentage": 10.42, "elapsed_time": "0:03:44", "remaining_time": "0:32:06"}
{"current_steps": 30, "total_steps": 192, "loss": 0.18245965242385864, "lr": 9.932595378142233e-06, "epoch": 0.47058823529411764, "percentage": 15.62, "elapsed_time": "0:05:27", "remaining_time": "0:29:30"}
{"current_steps": 40, "total_steps": 192, "loss": 0.1605141878128052, "lr": 9.701923994199784e-06, "epoch": 0.6274509803921569, "percentage": 20.83, "elapsed_time": "0:07:15", "remaining_time": "0:27:34"}
{"current_steps": 50, "total_steps": 192, "loss": 0.158633816242218, "lr": 9.314825963771724e-06, "epoch": 0.7843137254901961, "percentage": 26.04, "elapsed_time": "0:08:58", "remaining_time": "0:25:30"}
{"current_steps": 60, "total_steps": 192, "loss": 0.15139737129211425, "lr": 8.784179514331683e-06, "epoch": 0.9411764705882353, "percentage": 31.25, "elapsed_time": "0:10:42", "remaining_time": "0:23:34"}
{"current_steps": 70, "total_steps": 192, "loss": 0.1387779712677002, "lr": 8.127638534938227e-06, "epoch": 1.0941176470588236, "percentage": 36.46, "elapsed_time": "0:12:28", "remaining_time": "0:21:44"}
{"current_steps": 80, "total_steps": 192, "loss": 0.12184641361236573, "lr": 7.367045255243217e-06, "epoch": 1.2509803921568627, "percentage": 41.67, "elapsed_time": "0:14:12", "remaining_time": "0:19:53"}
{"current_steps": 90, "total_steps": 192, "loss": 0.11027407646179199, "lr": 6.527703584078219e-06, "epoch": 1.4078431372549018, "percentage": 46.88, "elapsed_time": "0:16:04", "remaining_time": "0:18:13"}
{"current_steps": 100, "total_steps": 192, "loss": 0.11028397083282471, "lr": 5.63753728266054e-06, "epoch": 1.5647058823529412, "percentage": 52.08, "elapsed_time": "0:17:49", "remaining_time": "0:16:23"}
{"current_steps": 110, "total_steps": 192, "loss": 0.10918575525283813, "lr": 4.726160978856782e-06, "epoch": 1.7215686274509805, "percentage": 57.29, "elapsed_time": "0:19:33", "remaining_time": "0:14:34"}
{"current_steps": 120, "total_steps": 192, "loss": 0.0961656391620636, "lr": 3.823894928601822e-06, "epoch": 1.8784313725490196, "percentage": 62.5, "elapsed_time": "0:21:17", "remaining_time": "0:12:46"}
{"current_steps": 130, "total_steps": 192, "loss": 0.08220374584197998, "lr": 2.9607563020271446e-06, "epoch": 2.0313725490196077, "percentage": 67.71, "elapsed_time": "0:23:10", "remaining_time": "0:11:03"}
{"current_steps": 140, "total_steps": 192, "loss": 0.05620207190513611, "lr": 2.1654605528435774e-06, "epoch": 2.1882352941176473, "percentage": 72.92, "elapsed_time": "0:25:03", "remaining_time": "0:09:18"}
{"current_steps": 150, "total_steps": 192, "loss": 0.06362113952636719, "lr": 1.4644660940672628e-06, "epoch": 2.3450980392156864, "percentage": 78.12, "elapsed_time": "0:26:48", "remaining_time": "0:07:30"}
{"current_steps": 160, "total_steps": 192, "loss": 0.063688462972641, "lr": 8.810940624342784e-07, "epoch": 2.5019607843137255, "percentage": 83.33, "elapsed_time": "0:28:37", "remaining_time": "0:05:43"}
{"current_steps": 170, "total_steps": 192, "loss": 0.05568122863769531, "lr": 4.347524557502919e-07, "epoch": 2.6588235294117646, "percentage": 88.54, "elapsed_time": "0:30:21", "remaining_time": "0:03:55"}
{"current_steps": 180, "total_steps": 192, "loss": 0.05975309610366821, "lr": 1.4029045507537696e-07, "epoch": 2.8156862745098037, "percentage": 93.75, "elapsed_time": "0:32:05", "remaining_time": "0:02:08"}
{"current_steps": 190, "total_steps": 192, "loss": 0.052491509914398195, "lr": 7.5044125708712e-09, "epoch": 2.9725490196078432, "percentage": 98.96, "elapsed_time": "0:33:50", "remaining_time": "0:00:21"}
{"current_steps": 192, "total_steps": 192, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:34:19", "remaining_time": "0:00:00"}

	{"current_steps": 10, "total_steps": 192, "loss": 0.408135986328125, "lr": 4.5e-06, "epoch": 0.1568627450980392, "percentage": 5.21, "elapsed_time": "0:01:53", "remaining_time": "0:34:30"}
	{"current_steps": 20, "total_steps": 192, "loss": 0.23105964660644532, "lr": 9.5e-06, "epoch": 0.3137254901960784, "percentage": 10.42, "elapsed_time": "0:03:44", "remaining_time": "0:32:06"}
	{"current_steps": 30, "total_steps": 192, "loss": 0.18245965242385864, "lr": 9.932595378142233e-06, "epoch": 0.47058823529411764, "percentage": 15.62, "elapsed_time": "0:05:27", "remaining_time": "0:29:30"}
	{"current_steps": 40, "total_steps": 192, "loss": 0.1605141878128052, "lr": 9.701923994199784e-06, "epoch": 0.6274509803921569, "percentage": 20.83, "elapsed_time": "0:07:15", "remaining_time": "0:27:34"}
	{"current_steps": 50, "total_steps": 192, "loss": 0.158633816242218, "lr": 9.314825963771724e-06, "epoch": 0.7843137254901961, "percentage": 26.04, "elapsed_time": "0:08:58", "remaining_time": "0:25:30"}
	{"current_steps": 60, "total_steps": 192, "loss": 0.15139737129211425, "lr": 8.784179514331683e-06, "epoch": 0.9411764705882353, "percentage": 31.25, "elapsed_time": "0:10:42", "remaining_time": "0:23:34"}
	{"current_steps": 70, "total_steps": 192, "loss": 0.1387779712677002, "lr": 8.127638534938227e-06, "epoch": 1.0941176470588236, "percentage": 36.46, "elapsed_time": "0:12:28", "remaining_time": "0:21:44"}
	{"current_steps": 80, "total_steps": 192, "loss": 0.12184641361236573, "lr": 7.367045255243217e-06, "epoch": 1.2509803921568627, "percentage": 41.67, "elapsed_time": "0:14:12", "remaining_time": "0:19:53"}
	{"current_steps": 90, "total_steps": 192, "loss": 0.11027407646179199, "lr": 6.527703584078219e-06, "epoch": 1.4078431372549018, "percentage": 46.88, "elapsed_time": "0:16:04", "remaining_time": "0:18:13"}
	{"current_steps": 100, "total_steps": 192, "loss": 0.11028397083282471, "lr": 5.63753728266054e-06, "epoch": 1.5647058823529412, "percentage": 52.08, "elapsed_time": "0:17:49", "remaining_time": "0:16:23"}
	{"current_steps": 110, "total_steps": 192, "loss": 0.10918575525283813, "lr": 4.726160978856782e-06, "epoch": 1.7215686274509805, "percentage": 57.29, "elapsed_time": "0:19:33", "remaining_time": "0:14:34"}
	{"current_steps": 120, "total_steps": 192, "loss": 0.0961656391620636, "lr": 3.823894928601822e-06, "epoch": 1.8784313725490196, "percentage": 62.5, "elapsed_time": "0:21:17", "remaining_time": "0:12:46"}
	{"current_steps": 130, "total_steps": 192, "loss": 0.08220374584197998, "lr": 2.9607563020271446e-06, "epoch": 2.0313725490196077, "percentage": 67.71, "elapsed_time": "0:23:10", "remaining_time": "0:11:03"}
	{"current_steps": 140, "total_steps": 192, "loss": 0.05620207190513611, "lr": 2.1654605528435774e-06, "epoch": 2.1882352941176473, "percentage": 72.92, "elapsed_time": "0:25:03", "remaining_time": "0:09:18"}
	{"current_steps": 150, "total_steps": 192, "loss": 0.06362113952636719, "lr": 1.4644660940672628e-06, "epoch": 2.3450980392156864, "percentage": 78.12, "elapsed_time": "0:26:48", "remaining_time": "0:07:30"}
	{"current_steps": 160, "total_steps": 192, "loss": 0.063688462972641, "lr": 8.810940624342784e-07, "epoch": 2.5019607843137255, "percentage": 83.33, "elapsed_time": "0:28:37", "remaining_time": "0:05:43"}
	{"current_steps": 170, "total_steps": 192, "loss": 0.05568122863769531, "lr": 4.347524557502919e-07, "epoch": 2.6588235294117646, "percentage": 88.54, "elapsed_time": "0:30:21", "remaining_time": "0:03:55"}
	{"current_steps": 180, "total_steps": 192, "loss": 0.05975309610366821, "lr": 1.4029045507537696e-07, "epoch": 2.8156862745098037, "percentage": 93.75, "elapsed_time": "0:32:05", "remaining_time": "0:02:08"}
	{"current_steps": 190, "total_steps": 192, "loss": 0.052491509914398195, "lr": 7.5044125708712e-09, "epoch": 2.9725490196078432, "percentage": 98.96, "elapsed_time": "0:33:50", "remaining_time": "0:00:21"}
	{"current_steps": 192, "total_steps": 192, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:34:19", "remaining_time": "0:00:00"}