Instructions to use Data-Selection/BSL-470M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Data-Selection/BSL-470M with Transformers:

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

pipe = pipeline("text-generation", model="Data-Selection/BSL-470M", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Data-Selection/BSL-470M")
model = AutoModelForCausalLM.from_pretrained("Data-Selection/BSL-470M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Data-Selection/BSL-470M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Data-Selection/BSL-470M"
# 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-470M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Data-Selection/BSL-470M

SGLang

How to use Data-Selection/BSL-470M 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-470M" \
    --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-470M",
		"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-470M" \
        --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-470M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Data-Selection/BSL-470M with Docker Model Runner:
```
docker model run hf.co/Data-Selection/BSL-470M
```

t1101675 commited on Oct 28, 2024

Commit

1581b9d

verified ·

1 Parent(s): 70f8583

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -8,13 +8,13 @@ pipeline_tag: text-generation
 library_name: transformers
 ---
-## BSL-160M
 [paper](https://arxiv.org/abs/2410.07064) | [code](https://github.com/microsoft/LMOps/tree/main/data_selection)
-**BSL-160M** is a 160M model with [Mistral](https://arxiv.org/abs/2310.06825) achitecture pre-trained from scratch on the CC split of [Redpajama](https://github.com/togethercomputer/RedPajama-Data).
-**It is used as the baseline for [PDS-160M](https://huggingface.co/Data-Selection/PDS-160M).**
 ### Evaluation

 library_name: transformers
 ---
+## BSL-470M
 [paper](https://arxiv.org/abs/2410.07064) | [code](https://github.com/microsoft/LMOps/tree/main/data_selection)
+**BSL-470M** is a 470M model with [Mistral](https://arxiv.org/abs/2310.06825) achitecture pre-trained from scratch on the CC split of [Redpajama](https://github.com/togethercomputer/RedPajama-Data).
+**It is used as the baseline for [PDS-470M](https://huggingface.co/Data-Selection/PDS-470M).**
 ### Evaluation