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")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kaleidoscopicwhether/svg-gen-weights", dtype="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 Generation Model Weights

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

Author: Ivan Aristy (NYU Tandon, CS-GY 9223 / ECE-GY 7123) Base Model: Qwen/Qwen2.5-Coder-1.5B-Instruct Best Public Score: 16.87 / 100 GitHub: ivanearisty/svg-gen

Models

Model	Type	Public Score	Description
componly-r32-adapter	LoRA adapter	16.87	Best model. Requires `merged-1.5b-r16` as base. LoRA r=32, alpha=64, trained on 45k competition-only samples.
merged-1.5b-r16	Full model	—	Qwen2.5-Coder-1.5B with Round 1 LoRA r=16 adapter permanently merged into weights. Base for the best adapter.
refined-7000	Full model	16.26	Full fine-tune from merged base, checkpoint 7000, CE loss 0.308. Standalone model.
r16-3epoch	LoRA adapter	15.47	Round 1 adapter. LoRA r=16, 3 epochs on 46k competition data. Load on `Qwen/Qwen2.5-Coder-1.5B-Instruct`.
mixed-r32-adapter	LoRA adapter	14.64	LoRA r=32, trained on 76k mixed data (competition + external). External data hurt performance.
codegen-1.5b	Full model	12.26	Code generation experiment — model outputs Python code instead of raw SVG.

Training Strategy

We use an iterative merge-and-retrain approach:

Round 1: LoRA r=16 on Qwen2.5-Coder-1.5B (46k competition data, 3 epochs)
Merge adapter into base weights
Round 2: Fresh LoRA r=32 on merged base (45k competition data, 2 epochs) — best model
Round 3: Merge Round 2 adapter, full fine-tune on DGX Spark

Key Findings

System prompt is critical: Removing it drops score from 53.8 to 18.8 (local ablation)
Less is more: Minimal system prompt ("Output valid SVG code only.") outperforms verbose prompts
LoRA > Full fine-tune: Despite lower CE loss, full fine-tuning scores worse than LoRA
Competition data only: External datasets (SVGX, OmniSVG) degraded performance
Greedy decoding optimal: Any sampling or penalty variation hurts structured SVG output

Hardware

Training (QLoRA): NVIDIA RTX 2000 Ada (16GB VRAM)
Training (Full FT): NVIDIA DGX Spark (128GB unified memory)
Inference: RTX 2000 Ada, 4-bit quantized, ~20s per SVG

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for kaleidoscopicwhether/svg-gen-weights

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B-Instruct

Adapter

(124)

this model