Image-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen3_5
html-generation
web-design
visual-ui
visual-question-answering
reasoning
zero-system-prompt
cot-purity
conversational
Instructions to use wesjos/Qwen3.5-9B-HTML-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wesjos/Qwen3.5-9B-HTML-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="wesjos/Qwen3.5-9B-HTML-v2") 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)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("wesjos/Qwen3.5-9B-HTML-v2") model = AutoModelForMultimodalLM.from_pretrained("wesjos/Qwen3.5-9B-HTML-v2", 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=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use wesjos/Qwen3.5-9B-HTML-v2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wesjos/Qwen3.5-9B-HTML-v2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wesjos/Qwen3.5-9B-HTML-v2", "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/wesjos/Qwen3.5-9B-HTML-v2
- SGLang
How to use wesjos/Qwen3.5-9B-HTML-v2 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 "wesjos/Qwen3.5-9B-HTML-v2" \ --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": "wesjos/Qwen3.5-9B-HTML-v2", "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 "wesjos/Qwen3.5-9B-HTML-v2" \ --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": "wesjos/Qwen3.5-9B-HTML-v2", "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 wesjos/Qwen3.5-9B-HTML-v2 with Docker Model Runner:
docker model run hf.co/wesjos/Qwen3.5-9B-HTML-v2
Update chat_template.jinja
Browse files- chat_template.jinja +2 -2
chat_template.jinja
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
{{- messages[0]['content'] }}
|
| 5 |
{%- else %}
|
| 6 |
-
{{- 'You are
|
| 7 |
{%- endif %}
|
| 8 |
{{- "\n\n# 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>" }}
|
| 9 |
{%- for tool in tools %}
|
|
@@ -15,7 +15,7 @@
|
|
| 15 |
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
{%- else %}
|
| 18 |
-
{{- '<|im_start|>system\nYou are
|
| 19 |
{%- endif %}
|
| 20 |
{%- endif %}
|
| 21 |
{%- for message in messages %}
|
|
|
|
| 3 |
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
{{- messages[0]['content'] }}
|
| 5 |
{%- else %}
|
| 6 |
+
{{- 'You are Mario-html. You are a helpful assistant.' }}
|
| 7 |
{%- endif %}
|
| 8 |
{{- "\n\n# 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>" }}
|
| 9 |
{%- for tool in tools %}
|
|
|
|
| 15 |
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Mario-html. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
{%- endif %}
|
| 20 |
{%- endif %}
|
| 21 |
{%- for message in messages %}
|