Instructions to use synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0 with Transformers:

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

pipe = pipeline("text-generation", model="synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0")
model = AutoModelForCausalLM.from_pretrained("synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0

SGLang

How to use synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0 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 "synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0" \
    --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": "synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0",
		"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 "synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0" \
        --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": "synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0 with Docker Model Runner:
```
docker model run hf.co/synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0
```

Model Details

The model is trained on optimization trajectories of blackbox optimization methods evaluated on different optimization tasks. It's based on a Qwen3-type architecture. More details are described in the paper:

An Open-Source Training Dataset for Foundation Models for Black-box Optimization Aaron Klein, Herilalaina Rakotoarison, Luca Thale-Bombien, David Salinas arXiv:2605.23417 [cs.LG]

Downstream Use

For an example how to use this model for optimization see the Syne-Tune library.

Training Details

Training Data

The model is trained on the BBO-Pile dataset.

Training Procedure

We used AdamW with β1 = 0.9, β2 = 0.95, weight_decay = 0.1, gradient clipping with max_norm = 1.0, and a cosine learning rate schedule with 10% linear warm-up. All models are trained with bf16-mixed, without gradient accumulation, and a context length of 4096 tokens

Citation

If you want to use this model please cite the following paper:

BibTeX:

@article{bbo-pile2026, title={An Open-Source Training Dataset for Foundation Models for Black-box Optimization}, author={Aaron Klein and Herilalaina Rakotoarison and Luca Thale-Bombien and David Salinas}, year={2026}, journal={arXiv:2605.23417 [cs.LG]} }

Downloads last month: 92

Safetensors

Model size

77.6M params

Tensor type

F32

Dataset used to train synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0

Collection including synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0

BBO-Pile Checkpoints

Collection

Checkpoints trained on the BBO-Pile dataset. More details: https://arxiv.org/pdf/2605.23417 • 24 items • Updated Jun 20 • 1

Paper for synetune/qwen3_80M_token_2B_lr_5e-3_bsz_16_seed_0

An Open-Source Training Dataset for Foundation Models for Black-box Optimization

Paper • 2605.23417 • Published May 22 • 1