Image-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen3_5
html-generation
web-design
visual-ui
visual-question-answering
reasoning
vllm
80k-context
zero-system-prompt
conversational
Instructions to use wesjos/Qwen3.5-4B-HTML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wesjos/Qwen3.5-4B-HTML with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="wesjos/Qwen3.5-4B-HTML") 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/Qwen3.5-4B-HTML") model = AutoModelForMultimodalLM.from_pretrained("wesjos/Qwen3.5-4B-HTML", 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/Qwen3.5-4B-HTML with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wesjos/Qwen3.5-4B-HTML" # 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/Qwen3.5-4B-HTML", "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/Qwen3.5-4B-HTML
- SGLang
How to use wesjos/Qwen3.5-4B-HTML 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/Qwen3.5-4B-HTML" \ --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/Qwen3.5-4B-HTML", "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/Qwen3.5-4B-HTML" \ --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/Qwen3.5-4B-HTML", "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/Qwen3.5-4B-HTML with Docker Model Runner:
docker model run hf.co/wesjos/Qwen3.5-4B-HTML
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,8 +17,10 @@ tags:
|
|
| 17 |
- 80k-context
|
| 18 |
- zero-system-prompt
|
| 19 |
---
|
| 20 |
-
#
|
| 21 |
-
-
|
|
|
|
|
|
|
| 22 |
# 🍄 Mario-HTML-4B
|
| 23 |
|
| 24 |
A visual-UI language model fine-tuned from **Qwen3.5-4B**. It answers in a small semantic HTML
|
|
|
|
| 17 |
- 80k-context
|
| 18 |
- zero-system-prompt
|
| 19 |
---
|
| 20 |
+
## Note
|
| 21 |
+
- This is a small experiment I conducted to see what happens if I choose to use HTML instead of Markdown in LLM.
|
| 22 |
+
- there are html tokens in Cot in this model which is low efficent for any task, because models have to waste there energy to think about how to make nice html. ill try to fix that.
|
| 23 |
+
- for the name mario, that is just because i was thinking of Marshroom LOL.
|
| 24 |
# 🍄 Mario-HTML-4B
|
| 25 |
|
| 26 |
A visual-UI language model fine-tuned from **Qwen3.5-4B**. It answers in a small semantic HTML
|