Instructions to use Zaixi/STELLA-VLM-32b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zaixi/STELLA-VLM-32b with Transformers:

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

pipe = pipeline("image-text-to-text", model="Zaixi/STELLA-VLM-32b")
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("Zaixi/STELLA-VLM-32b")
model = AutoModelForImageTextToText.from_pretrained("Zaixi/STELLA-VLM-32b")
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 Zaixi/STELLA-VLM-32b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zaixi/STELLA-VLM-32b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Zaixi/STELLA-VLM-32b",
		"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/Zaixi/STELLA-VLM-32b

SGLang

How to use Zaixi/STELLA-VLM-32b 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 "Zaixi/STELLA-VLM-32b" \
    --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": "Zaixi/STELLA-VLM-32b",
		"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 "Zaixi/STELLA-VLM-32b" \
        --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": "Zaixi/STELLA-VLM-32b",
		"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 Zaixi/STELLA-VLM-32b with Docker Model Runner:
```
docker model run hf.co/Zaixi/STELLA-VLM-32b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

STELLA-VLM-32b

STELLA-VLM-32b is a fine-tuned version of Qwen2.5-VL-32B-Instruct using Group Relative Policy Optimization (GRPO) with LoRA.

Model Details

Base Model: Qwen/Qwen2.5-VL-32B-Instruct
Fine-tuning Method: GRPO (Group Relative Policy Optimization) with LoRA (rank=64)
Training Data: Scientific protocol datasets (jove_llamafactory, finebio)
Parameters: 34B total parameters with 566M trainable LoRA parameters (1.66%)

Training Configuration

LoRA rank: 64
LoRA alpha: 128
Training epochs: 3 (checkpoint saved at step 400)
Batch size: 4
Learning rate: 2e-4
Reward function: Rule-based with length and repetition penalties

Usage

from transformers import AutoModelForVision2Seq, AutoProcessor
import torch

model = AutoModelForVision2Seq.from_pretrained(
    "Zaixi/STELLA-VLM-32b",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True
)
processor = AutoProcessor.from_pretrained("Zaixi/STELLA-VLM-32b", trust_remote_code=True)

Fine-tuning Details

This model was fine-tuned using GRPO on scientific protocol datasets to improve instruction following and consistency in generating scientific content. The model shows improved performance on:

Scientific protocol understanding
Consistent response generation
Following detailed instructions
Multimodal reasoning tasks

License

Apache 2.0

Downloads last month: 7

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for Zaixi/STELLA-VLM-32b

Base model

Qwen/Qwen2.5-VL-32B-Instruct

Finetuned

(67)

this model

Quantizations

2 models