Instructions to use objectai/obj_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use objectai/obj_v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="objectai/obj_v1")
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("objectai/obj_v1")
model = AutoModelForMultimodalLM.from_pretrained("objectai/obj_v1", 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 objectai/obj_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "objectai/obj_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "objectai/obj_v1",
		"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/objectai/obj_v1

SGLang

How to use objectai/obj_v1 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 "objectai/obj_v1" \
    --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": "objectai/obj_v1",
		"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 "objectai/obj_v1" \
        --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": "objectai/obj_v1",
		"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 objectai/obj_v1 with Docker Model Runner:
```
docker model run hf.co/objectai/obj_v1
```

rachitpandey26 commited on 6 days ago

Commit

a0baede

verified ·

1 Parent(s): 799e302

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -87,8 +87,7 @@ Set `temperature=0.0` so the same page yields the same answer.
 | Precision | bf16 (Ampere or newer; use fp16 below that) |
 | Context | 16384 covers the longest documents |
 Runs on an L4, A10G, L40S, A100 or RTX 4090. On a T4 add `--dtype float16`.
-Long documents matter: `bank_statement` and `form16` answers run to ~2500
-tokens, so `max_tokens` below 4096 truncates them mid-JSON.
 ## Output
 Compact JSON matching the requested schema. Fields absent from the page come
 back `null` rather than guessed. Values found on the page that the schema did

 | Precision | bf16 (Ampere or newer; use fp16 below that) |
 | Context | 16384 covers the longest documents |
 Runs on an L4, A10G, L40S, A100 or RTX 4090. On a T4 add `--dtype float16`.
 ## Output
 Compact JSON matching the requested schema. Fields absent from the page come
 back `null` rather than guessed. Values found on the page that the schema did