Instructions to use Adocados/GTA1-32B-vllm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Adocados/GTA1-32B-vllm with Transformers:

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

pipe = pipeline("image-text-to-text", model="Adocados/GTA1-32B-vllm", trust_remote_code=True)
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Adocados/GTA1-32B-vllm", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("Adocados/GTA1-32B-vllm", trust_remote_code=True, 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Adocados/GTA1-32B-vllm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Adocados/GTA1-32B-vllm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Adocados/GTA1-32B-vllm",
		"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/Adocados/GTA1-32B-vllm

SGLang

How to use Adocados/GTA1-32B-vllm 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 "Adocados/GTA1-32B-vllm" \
    --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": "Adocados/GTA1-32B-vllm",
		"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 "Adocados/GTA1-32B-vllm" \
        --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": "Adocados/GTA1-32B-vllm",
		"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 Adocados/GTA1-32B-vllm with Docker Model Runner:
```
docker model run hf.co/Adocados/GTA1-32B-vllm
```

GTA1-32B-vllm

File size: 1,382 Bytes

{
  "architectures": ["Qwen2_5_VLForConditionalGeneration"],
  "model_type": "qwen2_5_vl",
  "transformers_version": "4.49.0",
  "torch_dtype": "bfloat16",

  "processor_class": "OpenCUAProcessor",

  "hidden_act": "silu",
  "attention_dropout": 0.0,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "use_cache": true,

  "vocab_size": 152064,
  "max_position_embeddings": 128000,
  "sliding_window": 32768,
  "use_sliding_window": false,
  "max_window_layers": 64,

  "rope_scaling": { "type": "default" },
  "rope_theta": 1000000.0,

  "hidden_size": 5120,
  "intermediate_size": 27648,
  "num_hidden_layers": 64,
  "num_attention_heads": 40,
  "num_key_value_heads": 8,

  "bos_token_id": 151643,
  "eos_token_id": 151644,
  "pad_token_id": 152063,

  "vision_start_token_id": 151665,
  "vision_end_token_id": 151666,
  "image_token_id": 151667,
  "video_token_id": 151668,

  "vision_config": {
    "model_type": "qwen2_5_vl",
    "in_chans": 3,
    "hidden_size": 1280,
    "intermediate_size": 3456,
    "out_hidden_size": 5120,
    "spatial_patch_size": 14,
    "tokens_per_second": 2,
    "torch_dtype": "bfloat16"
  },

  "auto_map": {
    "AutoTokenizer": "tokenization_opencua.TikTokenV3",
    "AutoProcessor": "processing_opencua.OpenCUAProcessor",
    "AutoImageProcessor": "image_processing_qwen2_vl.Qwen2VLImageProcessor"
  }
}