Instructions to use Norod78/gpt-fluentui-flat-svg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Norod78/gpt-fluentui-flat-svg with Transformers:

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

pipe = pipeline("text-generation", model="Norod78/gpt-fluentui-flat-svg")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Norod78/gpt-fluentui-flat-svg")
model = AutoModelForCausalLM.from_pretrained("Norod78/gpt-fluentui-flat-svg")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Norod78/gpt-fluentui-flat-svg with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Norod78/gpt-fluentui-flat-svg"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Norod78/gpt-fluentui-flat-svg",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Norod78/gpt-fluentui-flat-svg

SGLang

How to use Norod78/gpt-fluentui-flat-svg 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 "Norod78/gpt-fluentui-flat-svg" \
    --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": "Norod78/gpt-fluentui-flat-svg",
		"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 "Norod78/gpt-fluentui-flat-svg" \
        --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": "Norod78/gpt-fluentui-flat-svg",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Norod78/gpt-fluentui-flat-svg with Docker Model Runner:
```
docker model run hf.co/Norod78/gpt-fluentui-flat-svg
```

gpt-fluentui-flat-svg

A custom GPT model which was trained upon svg files. Specifically the flat emoji variants from Microsoft's FluentUI repo. These svn files only consist of "stand-alone" path elements which should make it simpler to train upon and sample from.

training and dataset

Both Tokenizer and Model were trained using aitextgen The python file which was used for training, the .txt file dataset and a few generated samples can be found here

post processing and extracting .svg files from generated samples

    # Extract from generated output and into a seperate .svg file all sequences which starts with <svg and ends with:
    #  A. </svg>
    #  B. If the sequence does not end with </svg> then find the last > in the sequence and append </svg> to it

generated samples

The generated samples below were also created with this script

Downloads last month: 836

Safetensors

Model size

0.2B params

Tensor type

F32

Norod78
/

gpt-fluentui-flat-svg

gpt-fluentui-flat-svg

training and dataset

post processing and extracting .svg files from generated samples

generated samples

Spaces using Norod78/gpt-fluentui-flat-svg 17