Image-Text-to-Text
Transformers
Safetensors
qwen3_5
thinking_modes
qwen3.5
grape
vision
multimodal
instruct
chat
coding
math
science
reasoning
creative_writing
roleplay
conversational
Instructions to use SL-AI/GRaPE-2.5-Helios with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SL-AI/GRaPE-2.5-Helios with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="SL-AI/GRaPE-2.5-Helios") 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, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("SL-AI/GRaPE-2.5-Helios") model = AutoModelForMultimodalLM.from_pretrained("SL-AI/GRaPE-2.5-Helios", device_map="auto") 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 Settings
- vLLM
How to use SL-AI/GRaPE-2.5-Helios with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SL-AI/GRaPE-2.5-Helios" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SL-AI/GRaPE-2.5-Helios", "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/SL-AI/GRaPE-2.5-Helios
- SGLang
How to use SL-AI/GRaPE-2.5-Helios 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 "SL-AI/GRaPE-2.5-Helios" \ --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": "SL-AI/GRaPE-2.5-Helios", "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 "SL-AI/GRaPE-2.5-Helios" \ --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": "SL-AI/GRaPE-2.5-Helios", "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 SL-AI/GRaPE-2.5-Helios with Docker Model Runner:
docker model run hf.co/SL-AI/GRaPE-2.5-Helios
| { | |
| "add_prefix_space": false, | |
| "audio_bos_token": "<|audio_start|>", | |
| "audio_eos_token": "<|audio_end|>", | |
| "audio_token": "<|audio_pad|>", | |
| "backend": "tokenizers", | |
| "bos_token": null, | |
| "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- set add_vision_id = add_vision_id if add_vision_id is defined else false %}\n{%- set enable_thinking = enable_thinking if enable_thinking is defined else true %}\n{%- set _preserve_thinking = preserve_thinking if preserve_thinking is defined else true %}\n{%- set ns_state = namespace(thinking=enable_thinking) %}\n\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if item is mapping %}\n {%- if item.type == 'image' or 'image' in item or 'image_url' in item %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif item.type == 'video' or 'video' in item %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- else %}\n {{- item | string }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n\n{%- set _first_role = messages[0].role %}\n{%- if _first_role == 'system' or _first_role == 'developer' %}\n {%- set _sys_msg = messages[0] %}\n {%- set _msgs = messages[1:] %}\n{%- else %}\n {%- set _sys_msg = none %}\n {%- set _msgs = messages %}\n{%- endif %}\n\n{%- set _sc = '' %}\n{%- if _sys_msg is not none %}\n {%- set _sc = render_content(_sys_msg.content, false, true) | trim %}\n{%- endif %}\n\n{%- if _sc %}\n {{- '<|im_start|>system\\n' + _sc + '<|im_end|>\\n' }}\n{%- endif %}\n\n{%- set _last_idx = _msgs | length - 1 %}\n{%- set ns = namespace(last_query_index=_last_idx) %}\n\n{%- for message in _msgs[::-1] %}\n {%- set index = (_msgs | length - 1) - loop.index0 %}\n {%- if message.role == 'user' %}\n {%- set ns.last_query_index = index %}\n {%- break %}\n {%- endif %}\n{%- endfor %}\n\n{%- for message in _msgs %}\n {%- set is_system = (message.role == \"system\" or message.role == \"developer\") %}\n {%- set content = render_content(message.content, true, is_system) | trim %}\n\n {%- if is_system or message.role == 'user' %}\n {%- if '<|think_off|>' in content %}\n {%- set ns_state.thinking = false %}\n {%- set content = content.split('<|think_off|>') | join('') | trim %}\n {%- elif '<|think_on|>' in content %}\n {%- set ns_state.thinking = true %}\n {%- set content = content.split('<|think_on|>') | join('') | trim %}\n {%- endif %}\n {%- endif %}\n\n {%- if is_system %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n\n {%- elif message.role == 'user' %}\n {{- '<|im_start|>user\\n' + content + '<|im_end|>\\n' }}\n\n {%- elif message.role == 'assistant' %}\n {%- set reasoning_content = '' %}\n\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- set reasoning_content = message.reasoning_content | string %}\n {%- endif %}\n\n {%- elif message.thinking is defined and message.thinking is not none %}\n {%- if message.thinking is string %}\n {%- set reasoning_content = message.thinking %}\n {%- else %}\n {%- set reasoning_content = message.thinking | string %}\n {%- endif %}\n\n {%- else %}\n {%- set _think_end = '' %}\n\n {%- if content.startswith('</think>') %}\n {%- set _think_end = '</think>' %}\n {%- elif content.startswith('</thinking>') %}\n {%- set _think_end = '</thinking>' %}\n {%- elif '\\n</think>' in content %}\n {%- set _think_end = '\\n</think>' %}\n {%- elif '\\n</thinking>' in content %}\n {%- set _think_end = '\\n</thinking>' %}\n {%- elif '\\n</ think>' in content %}\n {%- set _think_end = '\\n</ think>' %}\n {%- elif '\\n</think >' in content %}\n {%- set _think_end = '\\n</think >' %}\n {%- endif %}\n\n {%- if _think_end %}\n {%- if 'thinking' in _think_end %}\n {%- set _think_start = '<thinking>' %}\n {%- else %}\n {%- set _think_start = '<think>' %}\n {%- endif %}\n\n {%- set reasoning_content = content.split(_think_end)[0].rstrip('\\n') %}\n\n {%- if _think_start in reasoning_content %}\n {%- set reasoning_content = reasoning_content.split(_think_start)[-1].lstrip('\\n') %}\n {%- endif %}\n\n {%- set content = content.split(_think_end)[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n\n {%- set reasoning_content = reasoning_content | trim %}\n\n {%- if (_preserve_thinking or loop.index0 > ns.last_query_index) and reasoning_content %}\n {{- '<|im_start|>assistant\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>assistant\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n\n {%- else %}\n {{- '<|im_start|>user\\n[' + message.role + ']: ' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "errors": "replace", | |
| "image_token": "<|image_pad|>", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "model_max_length": 262144, | |
| "model_specific_special_tokens": { | |
| "audio_bos_token": "<|audio_start|>", | |
| "audio_eos_token": "<|audio_end|>", | |
| "audio_token": "<|audio_pad|>", | |
| "image_token": "<|image_pad|>", | |
| "video_token": "<|video_pad|>", | |
| "vision_bos_token": "<|vision_start|>", | |
| "vision_eos_token": "<|vision_end|>" | |
| }, | |
| "pad_token": "<|endoftext|>", | |
| "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", | |
| "processor_class": "Qwen3VLProcessor", | |
| "split_special_tokens": false, | |
| "tokenizer_class": "Qwen2Tokenizer", | |
| "unk_token": null, | |
| "video_token": "<|video_pad|>", | |
| "vision_bos_token": "<|vision_start|>", | |
| "vision_eos_token": "<|vision_end|>" | |
| } | |