Image-Text-to-Text
Transformers
English
multilingual
llava
text-generation
multimodal
vision
long-context
function-calling
reasoning
conversational
Eval Results (legacy)
Instructions to use DeepXR/Helion-V2.0-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DeepXR/Helion-V2.0-Thinking with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="DeepXR/Helion-V2.0-Thinking") 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, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("DeepXR/Helion-V2.0-Thinking") model = AutoModelForCausalLM.from_pretrained("DeepXR/Helion-V2.0-Thinking") 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
- vLLM
How to use DeepXR/Helion-V2.0-Thinking with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DeepXR/Helion-V2.0-Thinking" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DeepXR/Helion-V2.0-Thinking", "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/DeepXR/Helion-V2.0-Thinking
- SGLang
How to use DeepXR/Helion-V2.0-Thinking 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 "DeepXR/Helion-V2.0-Thinking" \ --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": "DeepXR/Helion-V2.0-Thinking", "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 "DeepXR/Helion-V2.0-Thinking" \ --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": "DeepXR/Helion-V2.0-Thinking", "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 DeepXR/Helion-V2.0-Thinking with Docker Model Runner:
docker model run hf.co/DeepXR/Helion-V2.0-Thinking
Ctrl+K
- 1.52 kB
- 10.7 kB
- 6.41 kB
- 7.24 kB
- 12.3 kB
- 653 Bytes
- 15 kB
- 5.3 kB
- 1.61 kB
- 8.33 kB
- 13.8 kB
- 17.3 kB
- 609 Bytes
- 1.02 GB xet
- 969 MB xet
- 869 MB xet
- 872 MB xet
- 1.09 GB xet
- 1.01 GB xet
- 922 MB xet
- 1.05 GB xet
- 855 MB xet
- 967 MB xet
- 1.02 GB xet
- 1.1 GB xet
- 936 MB xet
- 1.07 GB xet
- 879 MB xet
- 970 MB xet
- 1.04 GB xet
- 969 MB xet
- 1.05 GB xet
- 1.1 GB xet
- 1.11 GB xet
- 965 MB xet
- 944 MB xet
- 1 GB xet
- 1.06 GB xet
- 1.04 GB xet
- 891 MB xet
- 965 MB xet
- 846 MB xet
- 993 MB xet
- 992 MB xet
- 897 MB xet
- 857 MB xet
- 1.03 GB xet
- 973 MB xet
- 1.07 GB xet
- 855 MB xet