Instructions to use ucsahin/TraVisionLM-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ucsahin/TraVisionLM-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="ucsahin/TraVisionLM-base", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ucsahin/TraVisionLM-base", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ucsahin/TraVisionLM-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ucsahin/TraVisionLM-base" # 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-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ucsahin/TraVisionLM-base
- SGLang
How to use ucsahin/TraVisionLM-base 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-base" \ --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-base", "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-base" \ --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-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ucsahin/TraVisionLM-base with Docker Model Runner:
docker model run hf.co/ucsahin/TraVisionLM-base
Update README.md
Browse files
README.md
CHANGED
|
@@ -352,7 +352,7 @@ The following compute resources are used in feature alignment and task specific
|
|
| 352 |
1xH100(80GB), took approximately 18 GPU hours.
|
| 353 |
|
| 354 |
|
| 355 |
-
## Citation
|
| 356 |
|
| 357 |
I am releasing TraVisionLM under the Apache 2.0 License. To the best of my knowledge after through research, this should comply with the datasets and unimodal vision and language models used during development.
|
| 358 |
|
|
|
|
| 352 |
1xH100(80GB), took approximately 18 GPU hours.
|
| 353 |
|
| 354 |
|
| 355 |
+
## License and Citation
|
| 356 |
|
| 357 |
I am releasing TraVisionLM under the Apache 2.0 License. To the best of my knowledge after through research, this should comply with the datasets and unimodal vision and language models used during development.
|
| 358 |
|