Instructions to use Data-Selection/BSL-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Data-Selection/BSL-1B with Transformers:

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

pipe = pipeline("text-generation", model="Data-Selection/BSL-1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Data-Selection/BSL-1B")
model = AutoModelForCausalLM.from_pretrained("Data-Selection/BSL-1B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Data-Selection/BSL-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Data-Selection/BSL-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Data-Selection/BSL-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Data-Selection/BSL-1B

SGLang

How to use Data-Selection/BSL-1B 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 "Data-Selection/BSL-1B" \
    --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": "Data-Selection/BSL-1B",
		"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 "Data-Selection/BSL-1B" \
        --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": "Data-Selection/BSL-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Data-Selection/BSL-1B with Docker Model Runner:
```
docker model run hf.co/Data-Selection/BSL-1B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

BSL-1B

paper | code

BSL-1B is a 1B model with Mistral achitecture pre-trained from scratch on the CC split of Redpajama.

It is used as the baseline for PDS-1B.

Evaluation

PDS-selected data improves the performance of language models pre-trained from scratch and saves pre-training comptation. The improvement scales up to large model sizes.

Citation

@article{gu2024data,
  title={Data Selection via Optimal Control for Language Models},
  author={Gu, Yuxian and Dong, Li and Wang, Hongning and Hao, Yaru and Dong, Qingxiu and Wei, Furu and Huang, Minlie},
  journal={arXiv preprint arXiv:2410.07064},
  year={2024}
}

Downloads last month: 6

Model tree for Data-Selection/BSL-1B

Quantizations

1 model

Dataset used to train Data-Selection/BSL-1B

Collection including Data-Selection/BSL-1B

Baseline Models

Collection

Models Trained on Redpajama-CC • 4 items • Updated Oct 8, 2024

Papers for Data-Selection/BSL-1B

Data Selection via Optimal Control for Language Models

Paper • 2410.07064 • Published Oct 9, 2024 • 9

Mistral 7B

Paper • 2310.06825 • Published Oct 10, 2023 • 58