Like 75

Follow

Apple 7.32k

Image-Text-to-Text

Transformers

Safetensors

qwen3_5

vision-language-model

long-context

visual-text-compression

conversational

arxiv: 2605.07019

License: apple-amlr

Model card Files Files and versions xet

Deploy

Copy to bucket new

Use this model Instructions to use apple/LensVLM-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers How to use apple/LensVLM-9B with Transformers:

Use a pipeline as a high-level helper

from transformers import pipeline

pipe = pipeline("image-text-to-text", model="apple/LensVLM-9B") 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("apple/LensVLM-9B") model = AutoModelForMultimodalLM.from_pretrained("apple/LensVLM-9B", 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 apple/LensVLM-9B with vLLM:

Install vLLM from pip:

pip install vllm

Start the vLLM server:

vllm serve "apple/LensVLM-9B"

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:8000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "apple/LensVLM-9B", "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/apple/LensVLM-9B

SGLang How to use apple/LensVLM-9B with SGLang:

Install SGLang from pip:

pip install sglang

Start the SGLang server:

python3 -m sglang.launch_server
--model-path "apple/LensVLM-9B"
--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": "apple/LensVLM-9B", "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 "apple/LensVLM-9B"
--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": "apple/LensVLM-9B", "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 apple/LensVLM-9B with Docker Model Runner:

docker model run hf.co/apple/LensVLM-9B

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LensVLM-9B License

Usage

Citation

LensVLM-9B

LensVLM is a 9B Vision Language Model (VLM) that scans compressed images of text, then selectively expands only the relevant pages to their uncompressed form via learned tools.

License

All ML model files in this repository, including Apple's modifications to the Qwen model, are provided under the terms of the Apple Machine Learning Research Model License.

The source code that accompanies this model is distributed separately and is provided under the terms of the Apple Sample Code License.

Usage

Install the LensVLM code and run inference:

git clone https://github.com/apple-aiml-research/ml-lensvlm cd ml-lensvlm pip install -r requirements.txt python scripts/run_demo.py --model apple/LensVLM-9B

For a custom document:

python demo.py
--model apple/LensVLM-9B
--text_file document.txt
--question "What is the main finding?"
--compression 10x

Compression options: 5x, 10x, 15x. See the repository README for data preparation and evaluation.

Citation

@article{xie2026lensvlm, title={LensVLM: Selective Context Expansion for Compressed Visual Representation of Text}, author={Xie, Roy and Friedman, Dan and Yu, Donghan and Pan, Bowen and Fifty, Christopher and Kim, Jang-Hyun and Du, Xianzhi and Gan, Zhe and Rathod, Vivek and Dhingra, Bhuwan}, journal={arXiv preprint arXiv:2605.07019}, year={2026} }

Downloads last month 233

","pad_token":"<|endoftext|>","unk_token":null},"chat_template_jinja":"{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\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 'image' in item or 'image_url' in item or item.type == 'image' %}\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 'video' in item or item.type == 'video' %}\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 {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\n' }}\n {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}\n {%- for tool in tools %}\n {{- "\n" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- "\n</tools>" }}\n {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\n\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == "user" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == "system" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == "user" %}\n {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}\n {%- elif message.role == "assistant" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}\n {%- else %}\n {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}\n {%- endif %}\n {%- else %}\n {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\n</parameter>\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == "tool" %}\n {%- if loop.previtem and loop.previtem.role != "tool" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\n<tool_response>\n' }}\n {{- content }}\n {{- '\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != "tool" %}\n {{- '<|im_end|>\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\n' }}\n {