Instructions to use Salesforce/GTA1-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/GTA1-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Salesforce/GTA1-7B")
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("Salesforce/GTA1-7B")
model = AutoModelForImageTextToText.from_pretrained("Salesforce/GTA1-7B")
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 Salesforce/GTA1-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/GTA1-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/GTA1-7B",
		"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/Salesforce/GTA1-7B

SGLang

How to use Salesforce/GTA1-7B 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 "Salesforce/GTA1-7B" \
    --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": "Salesforce/GTA1-7B",
		"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 "Salesforce/GTA1-7B" \
        --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": "Salesforce/GTA1-7B",
		"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 Salesforce/GTA1-7B with Docker Model Runner:
```
docker model run hf.co/Salesforce/GTA1-7B
```

GTA1-7B / tokenizer_config.json

HelloKKMe

Upload folder using huggingface_hub

d43fbcb verified 8 months ago

raw

history blame contribute delete

7.05 kB

	{
	"added_tokens_decoder": {
	"151643": {
	"content": "[BOS]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151644": {
	"content": "[EOS]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151645": {
	"content": "<\|im_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151646": {
	"content": "<\|im_user\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151647": {
	"content": "<\|im_assistant\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151648": {
	"content": "<\|reserved_token_0\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151649": {
	"content": "<\|start_header_id\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151650": {
	"content": "<\|end_header_id\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151651": {
	"content": "<\|reserved_token_1\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151652": {
	"content": "[EOT]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151653": {
	"content": "<\|im_system\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151654": {
	"content": "<\|reserved_token_2\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151655": {
	"content": "<\|reserved_token_3\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151656": {
	"content": "<\|reserved_token_4\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151657": {
	"content": "<\|reserved_token_5\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151658": {
	"content": "<\|reserved_token_6\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151659": {
	"content": "<\|reserved_token_7\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151660": {
	"content": "<\|im_middle\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151661": {
	"content": "<\|media_begin\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151662": {
	"content": "<\|media_content\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151663": {
	"content": "<\|media_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151664": {
	"content": "<\|media_placeholder\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151665": {
	"content": "<\|vision_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151666": {
	"content": "<\|vision_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151667": {
	"content": "<\|image_pad\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"151668": {
	"content": "<\|video_pad\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"152062": {
	"content": "[UNK]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"152063": {
	"content": "[PAD]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}

	},
	"additional_special_tokens": [
	"<\|im_end\|>",
	"<\|im_user\|>",
	"<\|im_assistant\|>",
	"<\|reserved_token_0\|>",
	"<\|start_header_id\|>",
	"<\|end_header_id\|>",
	"<\|reserved_token_1\|>",
	"[EOT]",
	"<\|im_system\|>",
	"<\|reserved_token_2\|>",
	"<\|reserved_token_3\|>",
	"<\|reserved_token_4\|>",
	"<\|reserved_token_5\|>",
	"<\|reserved_token_6\|>",
	"<\|reserved_token_7\|>",
	"<\|im_middle\|>",
	"<\|media_begin\|>",
	"<\|media_content\|>",
	"<\|media_end\|>",
	"<\|media_placeholder\|>",
	"<\|vision_start\|>",
	"<\|vision_end\|>",
	"<\|image_pad\|>",
	"<\|video_pad\|>"
	],
	"bos_token": "[BOS]",
	"clean_up_tokenization_spaces": false,
	"eos_token": "[EOS]",
	"extra_special_tokens": {},
	"chat_template": "{%- for message in messages -%}{%- if loop.first and messages[0]['role'] != 'system' -%}{{'<\|im_system\|>system<\|im_middle\|>You are a helpful assistant<\|im_end\|>'}}{%- endif -%}{%- if message['role'] == 'system' -%}{{'<\|im_system\|>'}}{%- endif -%}{%- if message['role'] == 'user' -%}{{'<\|im_user\|>'}}{%- endif -%}{%- if message['role'] == 'assistant' -%}{{'<\|im_assistant\|>'}}{%- endif -%}{{- message['role'] -}}{{'<\|im_middle\|>'}}{%- if message['content'] is string -%}{{- message['content'] + '<\|im_end\|>' -}}{%- else -%}{%- for content in message['content'] -%}{%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}{{'<\|media_begin\|>image<\|media_content\|><\|media_placeholder\|><\|media_end\|>'}}{%- else -%}{{content['text']}}{%- endif -%}{%- endfor -%}{{'<\|im_end\|>'}}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{'<\|im_assistant\|>assistant<\|im_middle\|>'}}{%- endif -%}",
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "[PAD]",
	"tokenizer_class": "Qwen2Tokenizer",
	"unk_token": "[UNK]",
	"auto_map": {
	"AutoTokenizer": [
	"tokenization_opencua.TikTokenV3",
	null
	]
	}
	}