Instructions to use ucsahin/TraVisionLM-Object-Detection-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ucsahin/TraVisionLM-Object-Detection-ft with Transformers:

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

pipe = pipeline("image-text-to-text", model="ucsahin/TraVisionLM-Object-Detection-ft", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ucsahin/TraVisionLM-Object-Detection-ft", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ucsahin/TraVisionLM-Object-Detection-ft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ucsahin/TraVisionLM-Object-Detection-ft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ucsahin/TraVisionLM-Object-Detection-ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ucsahin/TraVisionLM-Object-Detection-ft

SGLang

How to use ucsahin/TraVisionLM-Object-Detection-ft 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 "ucsahin/TraVisionLM-Object-Detection-ft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ucsahin/TraVisionLM-Object-Detection-ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ucsahin/TraVisionLM-Object-Detection-ft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ucsahin/TraVisionLM-Object-Detection-ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ucsahin/TraVisionLM-Object-Detection-ft with Docker Model Runner:
```
docker model run hf.co/ucsahin/TraVisionLM-Object-Detection-ft
```

TraVisionLM-Object-Detection-ft / preprocessor_config.json

ucsahin

Training in progress, step 570

79c2059 verified almost 2 years ago

raw

history blame contribute delete

536 Bytes

	{
	"auto_map": {
	"AutoProcessor": "ucsahin/TraVisionLM-base--processing_travisionlm.TraVisionProcessor"
	},
	"do_convert_rgb": null,
	"do_normalize": true,
	"do_rescale": true,
	"do_resize": true,
	"image_mean": [
	0.5,
	0.5,
	0.5
	],
	"image_processor_type": "SiglipImageProcessor",
	"image_seq_length": 256,
	"image_std": [
	0.5,
	0.5,
	0.5
	],
	"processor_class": "TraVisionProcessor",
	"resample": 3,
	"rescale_factor": 0.00392156862745098,
	"size": {
	"height": 256,
	"width": 256
	}
	}