Instructions to use tcz/rb-llama-90b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tcz/rb-llama-90b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="tcz/rb-llama-90b")
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("tcz/rb-llama-90b")
model = AutoModelForMultimodalLM.from_pretrained("tcz/rb-llama-90b")
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 tcz/rb-llama-90b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tcz/rb-llama-90b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tcz/rb-llama-90b",
		"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/tcz/rb-llama-90b

SGLang

How to use tcz/rb-llama-90b 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 "tcz/rb-llama-90b" \
    --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": "tcz/rb-llama-90b",
		"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 "tcz/rb-llama-90b" \
        --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": "tcz/rb-llama-90b",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use tcz/rb-llama-90b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tcz/rb-llama-90b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tcz/rb-llama-90b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tcz/rb-llama-90b to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="tcz/rb-llama-90b",
    max_seq_length=2048,
)

Docker Model Runner
How to use tcz/rb-llama-90b with Docker Model Runner:
```
docker model run hf.co/tcz/rb-llama-90b
```

Reverse Browser 90B Model

License: Apache-2.0
Finetuned from model : unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit

This is a vector-to-ui model. It was fine-tuned on the HTML+CSS code of hundreds of thousands of public web pages and their SVG counterparts.

The goal of the model is to aid rapid prototyping and web development.

The model was trained on mobile resolution (393×852) SVGs only. Its test set accuracy was 0.3012 LPIPS (AlexNet). This suggests that it is not ready for industrial use in a real workflow, but it may serve research purposes.

Usage

!pip install vllm

from vllm import LLM, SamplingParams
llm = LLM(
    "tcz/rb-llama-90b",  
    tensor_parallel_size=4,   # The was tested on four H100s (96GB) GPUs
    dtype="bfloat16",
    gpu_memory_utilization=0.9, 
    enforce_eager=True,         
    max_model_len=12_000,
    max_num_seqs=64,
)

data_prompt = """Your job is to take an SVG file of a web design and convert it into a pixel-perfect HTML and CSS markup and stylesheet.

### Input:
{}

### Response:
{}"""

max_tokens = 12_000

# Experiment with different temperature and top-p settings
sampling_params = SamplingParams(
    temperature   = 0.0,
    top_p         = 1.0,
    top_k         = 1,
    n             = 1,
    max_tokens    = max_tokens,
    seed          = 0
)

prompt = data_prompt.format(
    YOUR_SVG_CONTENT,
    "",
)

output = llm.generate([prompt], sampling_params)
print(output[0].outputs[0].text)