Instructions to use SamsungSAILMontreal/ByteCraft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SamsungSAILMontreal/ByteCraft with Transformers:

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

pipe = pipeline("text-generation", model="SamsungSAILMontreal/ByteCraft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SamsungSAILMontreal/ByteCraft")
model = AutoModelForCausalLM.from_pretrained("SamsungSAILMontreal/ByteCraft")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SamsungSAILMontreal/ByteCraft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SamsungSAILMontreal/ByteCraft

SGLang

How to use SamsungSAILMontreal/ByteCraft 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 "SamsungSAILMontreal/ByteCraft" \
    --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": "SamsungSAILMontreal/ByteCraft",
		"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 "SamsungSAILMontreal/ByteCraft" \
        --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": "SamsungSAILMontreal/ByteCraft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SamsungSAILMontreal/ByteCraft with Docker Model Runner:
```
docker model run hf.co/SamsungSAILMontreal/ByteCraft
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)

ByteCraft

ByteCraft is the world's first generative model of SWF video games and animations through bytes conditional on prompt.

For more details, please refer to our Blog, Paper/Tech-report, and Inference Code.

Reference

If you find our work useful, please consider citing:

@article{202503.1962,
    doi = {10.20944/preprints202503.1962.v1},
    url = {https://www.preprints.org/manuscript/202503.1962/v1},
    year = 2025,
    month = {March},
    publisher = {Preprints},
    author = {Alexia Jolicoeur-Martineau and Emy Gervais},
    title = {ByteCraft: Generating Video Games and Animations Through Bytes},
    journal = {Preprints}
}

Downloads last month: 11

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for SamsungSAILMontreal/ByteCraft

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(2576)

this model

Quantizations

3 models