Image-Text-to-Text
Transformers
Safetensors
vision
multimodal
decision-engine
non-autoregressive
classification
structured-output
agent-tools
function-calling
Instructions to use jaswanthsanjay88/rev-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jaswanthsanjay88/rev-vision with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="jaswanthsanjay88/rev-vision")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jaswanthsanjay88/rev-vision", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jaswanthsanjay88/rev-vision with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jaswanthsanjay88/rev-vision" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jaswanthsanjay88/rev-vision", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jaswanthsanjay88/rev-vision
- SGLang
How to use jaswanthsanjay88/rev-vision 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 "jaswanthsanjay88/rev-vision" \ --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": "jaswanthsanjay88/rev-vision", "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 "jaswanthsanjay88/rev-vision" \ --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": "jaswanthsanjay88/rev-vision", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jaswanthsanjay88/rev-vision with Docker Model Runner:
docker model run hf.co/jaswanthsanjay88/rev-vision
Download processor/tokenizer_config.json from jaswanthsanjay88/rev-vision: direct link, hf CLI and curl.
- Browser
- Download file 587 Bytes
-
https://huggingface.co/jaswanthsanjay88/rev-vision/resolve/main/processor/tokenizer_config.json
- Command line
-
hf download hf://jaswanthsanjay88/rev-vision/processor/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/jaswanthsanjay88/rev-vision/resolve/main/processor/tokenizer_config.json
587 Bytes
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": "<|im_start|>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<end_of_utterance>", | |
| "errors": "replace", | |
| "extra_special_tokens": [ | |
| "<fake_token_around_image>", | |
| "<image>", | |
| "<end_of_utterance>" | |
| ], | |
| "is_local": false, | |
| "legacy": false, | |
| "local_files_only": false, | |
| "model_max_length": 8192, | |
| "pad_token": "<|im_end|>", | |
| "processor_class": "Idefics3Processor", | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "truncation_side": "left", | |
| "unk_token": "<|endoftext|>", | |
| "vocab_size": 49152 | |
| } | |