Image-Text-to-Text
Transformers
Safetensors
step_robotics
text-generation
vLLM
AWQ
conversational
custom_code
4-bit precision
awq
Instructions to use QuantTrio/Step3-VL-10B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QuantTrio/Step3-VL-10B-AWQ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="QuantTrio/Step3-VL-10B-AWQ", 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 AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("QuantTrio/Step3-VL-10B-AWQ", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use QuantTrio/Step3-VL-10B-AWQ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "QuantTrio/Step3-VL-10B-AWQ" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "QuantTrio/Step3-VL-10B-AWQ", "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/QuantTrio/Step3-VL-10B-AWQ
- SGLang
How to use QuantTrio/Step3-VL-10B-AWQ 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 "QuantTrio/Step3-VL-10B-AWQ" \ --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": "QuantTrio/Step3-VL-10B-AWQ", "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 "QuantTrio/Step3-VL-10B-AWQ" \ --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": "QuantTrio/Step3-VL-10B-AWQ", "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 QuantTrio/Step3-VL-10B-AWQ with Docker Model Runner:
docker model run hf.co/QuantTrio/Step3-VL-10B-AWQ
| {% macro render_content(content) %}{% if content is none %}{{- '' }}{% elif content is string %}{{- content }}{% elif content is mapping %}{{- content['value'] if 'value' in content else content['text'] }}{% elif content is iterable %}{% for item in content %}{% if item.type == 'text' %}{{- item['value'] if 'value' in item else item['text'] }}{% elif item.type == 'image' %}<im_patch>{% endif %}{% endfor %}{% endif %}{% endmacro %} | |
| {%- if tools %} | |
| {{- '<|im_start|>system\n' }} | |
| {%- if messages[0].role == 'system' %} | |
| {{- render_content(messages[0].content) + '\n\n' }} | |
| {%- endif %} | |
| {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }} | |
| {%- for tool in tools %} | |
| {{- "\n" }} | |
| {{- tool | tojson }} | |
| {%- endfor %} | |
| {{- "\n</tools>\n\nAlways adhere to this exact format for tool use:\n<tool_calls>\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n{additional_tool_calls}</tool_calls>\n\nNote:\n- For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags.\n- `<function-name>` must be an exact match to one of the available tools.\n- `<args-json-object>` must be valid JSON that strictly follows the tool's parameters schema.<|im_end|>\n" }} | |
| {%- else %} | |
| {%- if messages[0].role == 'system' %} | |
| {{- '<|im_start|>system\n' + render_content(messages[0].content) + '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} | |
| {%- for message in messages[::-1] %} | |
| {%- set index = (messages|length - 1) - loop.index0 %} | |
| {%- if ns.multi_step_tool and message.role == "user" and render_content(message.content) is string and not(render_content(message.content).startswith('<tool_response>') and render_content(message.content).endswith('</tool_response>')) %} | |
| {%- set ns.multi_step_tool = false %} | |
| {%- set ns.last_query_index = index %} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- for message in messages %} | |
| {%- set content = render_content(message.content) %} | |
| {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} | |
| {%- set role_name = 'observation' if (message.role == "system" and not loop.first and message.name == 'observation') else message.role %} | |
| {{- '<|im_start|>' + role_name + '\n' + content + '<|im_end|>' + '\n' }} | |
| {%- elif message.role == "assistant" %} | |
| {%- if message.reasoning_content is string %} | |
| {%- set reasoning_content = render_content(message.reasoning_content) %} | |
| {%- else %} | |
| {%- if '</think>' in content %} | |
| {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %} | |
| {%- set content = content.split('</think>')[-1].lstrip('\n') %} | |
| {%- else %} | |
| {%- set reasoning_content = '' %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- if loop.index0 > ns.last_query_index %} | |
| {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n' + content }} | |
| {%- else %} | |
| {{- '<|im_start|>' + message.role + '\n' + content }} | |
| {%- endif %} | |
| {%- if message.tool_calls %} | |
| {{- '\n<tool_calls>' }} | |
| {%- for tool_call in message.tool_calls %} | |
| {{- '\n' }} | |
| {%- if tool_call.function %} | |
| {%- set tool_call = tool_call.function %} | |
| {%- endif %} | |
| {{- '<tool_call>\n{"name": "' }} | |
| {{- tool_call.name }} | |
| {{- '", "arguments": ' }} | |
| {%- if tool_call.arguments is string %} | |
| {{- tool_call.arguments }} | |
| {%- else %} | |
| {{- tool_call.arguments | tojson }} | |
| {%- endif %} | |
| {{- '}\n</tool_call>' }} | |
| {%- endfor %} | |
| {{- '\n</tool_calls>' }} | |
| {%- endif %} | |
| {{- '<|im_end|>\n' }} | |
| {%- elif message.role == "tool" %} | |
| {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} | |
| {{- '<|im_start|>tool_response' }} | |
| {%- endif %} | |
| {{- '\n<tool_response>\n' }} | |
| {{- content }} | |
| {{- '\n</tool_response>' }} | |
| {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} | |
| {{- '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- if add_generation_prompt %} | |
| {{- '<|im_start|>assistant\n<think>\n\n</think>\n' if (enable_thinking is defined and not enable_thinking) else '<|im_start|>assistant\n<think>' -}} | |
| {%- endif %} |