Image-Text-to-Text
Transformers
Safetensors
English
Chinese
feature-extraction
conversational
custom_code
Instructions to use FlashVL/FlashVL-2B-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FlashVL/FlashVL-2B-Dynamic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="FlashVL/FlashVL-2B-Dynamic", trust_remote_code=True) 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 AutoModel model = AutoModel.from_pretrained("FlashVL/FlashVL-2B-Dynamic", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use FlashVL/FlashVL-2B-Dynamic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FlashVL/FlashVL-2B-Dynamic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FlashVL/FlashVL-2B-Dynamic", "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/FlashVL/FlashVL-2B-Dynamic
- SGLang
How to use FlashVL/FlashVL-2B-Dynamic 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 "FlashVL/FlashVL-2B-Dynamic" \ --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": "FlashVL/FlashVL-2B-Dynamic", "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 "FlashVL/FlashVL-2B-Dynamic" \ --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": "FlashVL/FlashVL-2B-Dynamic", "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 FlashVL/FlashVL-2B-Dynamic with Docker Model Runner:
docker model run hf.co/FlashVL/FlashVL-2B-Dynamic
| from .mm_constants import IMAGE_TOKEN_INDEX, IMAGE_PAD_TOKEN_INDEX | |
| def tokenizer_image_token_qwen(prompt, tokenizer, image_token_index, image_token_num=256): | |
| prompt_chunks, tmp = [], [] | |
| for n in prompt: | |
| if n == image_token_index: | |
| prompt_chunks.append(tmp) | |
| tmp = [] | |
| else: | |
| tmp.append(n) | |
| if tmp: prompt_chunks.append(tmp) | |
| input_ids = [] | |
| for i, chunk in enumerate(prompt_chunks): | |
| if i > 0: | |
| input_ids.extend([IMAGE_TOKEN_INDEX] + [IMAGE_PAD_TOKEN_INDEX] * (image_token_num - 1)) | |
| input_ids.extend(chunk) | |
| return input_ids |