Instructions to use kaleidoscopicwhether/svg-gen-weights with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaleidoscopicwhether/svg-gen-weights with Transformers:

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

pipe = pipeline("text-generation", model="kaleidoscopicwhether/svg-gen-weights")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kaleidoscopicwhether/svg-gen-weights", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kaleidoscopicwhether/svg-gen-weights with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaleidoscopicwhether/svg-gen-weights"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaleidoscopicwhether/svg-gen-weights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kaleidoscopicwhether/svg-gen-weights

SGLang

How to use kaleidoscopicwhether/svg-gen-weights 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 "kaleidoscopicwhether/svg-gen-weights" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaleidoscopicwhether/svg-gen-weights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "kaleidoscopicwhether/svg-gen-weights" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaleidoscopicwhether/svg-gen-weights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kaleidoscopicwhether/svg-gen-weights with Docker Model Runner:
```
docker model run hf.co/kaleidoscopicwhether/svg-gen-weights
```

svg-gen-weights / README.md

kaleidoscopicwhether

Upload README.md with huggingface_hub

c78e661 verified 6 months ago

preview code

Raw History Blame

2.09 kB

SVG Generation Model Weights

Model weights for the DL Spring 2026 Kaggle Competition — Text-to-SVG Generation.

Team: Ivan Aristy (NYU Tandon) Final Score: 16.87/100 (6th place / 58 teams) Base Model: Qwen/Qwen2.5-Coder-1.5B-Instruct

Models

Model	Type	Kaggle Score	Description
`componly-r32-adapter`	LoRA adapter	16.87	Best model. Load on `merged-1.5b-r16`.
`refined-7000`	Full model	16.26	Full fine-tune, loss 0.308
`r16-3epoch`	LoRA adapter	15.47	First adapter, load on Qwen2.5-Coder-1.5B
`mixed-r32-adapter`	LoRA adapter	14.64	Mixed data experiment
`codegen-1.5b`	Full model	12.26	Code generation experiment
`merged-1.5b-r16`	Full model	—	Base model with r16 knowledge baked in

Usage (Best Model)

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel
import torch

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True, bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True,
)

# Load merged base
tokenizer = AutoTokenizer.from_pretrained("kaleidoscopicwhether/svg-gen-weights", subfolder="merged-1.5b-r16")
model = AutoModelForCausalLM.from_pretrained(
    "kaleidoscopicwhether/svg-gen-weights", subfolder="merged-1.5b-r16",
    quantization_config=bnb_config, device_map="auto", torch_dtype=torch.bfloat16,
)

# Load best adapter
model = PeftModel.from_pretrained(model, "kaleidoscopicwhether/svg-gen-weights", subfolder="componly-r32-adapter")
model.eval()

# Generate
prompt = "<|im_start|>system\nOutput valid SVG code only.<|im_end|>\n<|im_start|>user\nA red circle<|im_end|>\n<|im_start|>assistant\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=1024, do_sample=False, repetition_penalty=1.1)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Training Details

See GitHub repo and paper in report/main.pdf.