Instructions to use bradfordlevy/pythia-1.4b-bc-cp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bradfordlevy/pythia-1.4b-bc-cp with Transformers:

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

pipe = pipeline("text-generation", model="bradfordlevy/pythia-1.4b-bc-cp")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("bradfordlevy/pythia-1.4b-bc-cp")
model = AutoModelForMultimodalLM.from_pretrained("bradfordlevy/pythia-1.4b-bc-cp")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bradfordlevy/pythia-1.4b-bc-cp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bradfordlevy/pythia-1.4b-bc-cp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bradfordlevy/pythia-1.4b-bc-cp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bradfordlevy/pythia-1.4b-bc-cp

SGLang

How to use bradfordlevy/pythia-1.4b-bc-cp 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 "bradfordlevy/pythia-1.4b-bc-cp" \
    --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": "bradfordlevy/pythia-1.4b-bc-cp",
		"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 "bradfordlevy/pythia-1.4b-bc-cp" \
        --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": "bradfordlevy/pythia-1.4b-bc-cp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bradfordlevy/pythia-1.4b-bc-cp with Docker Model Runner:
```
docker model run hf.co/bradfordlevy/pythia-1.4b-bc-cp
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card

This model was created from EleutherAI's Pythia-1.4B model by continued pretraining on the BeanCounter dataset. Full details of the training process are available in Wang and Levy (2024). The model has not undergone any safety checks or alignment, thus it should be used for research purposes only.

If you use this model in your work, please cite us:

@inproceedings{
  wang2024beancounter,
  title={BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text},
  author={Siyan Wang and Bradford Levy},
  booktitle={The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
  year={2024},
  url={https://openreview.net/forum?id=HV5JhUZGpP}
}

Downloads last month: -

Safetensors

Model size

1B params

Tensor type

F32

Collection including bradfordlevy/pythia-1.4b-bc-cp

BeanCounter

Collection

An open dataset containing more than 150B tokens of low-toxicity and business-oriented text. • 4 items • Updated Dec 11, 2024

Paper for bradfordlevy/pythia-1.4b-bc-cp

BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text

Paper • 2409.17827 • Published Sep 26, 2024