Instructions to use datajuicer/LLaMA-1B-dj-refine-100B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use datajuicer/LLaMA-1B-dj-refine-100B with Transformers:

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

pipe = pipeline("text-generation", model="datajuicer/LLaMA-1B-dj-refine-100B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("datajuicer/LLaMA-1B-dj-refine-100B")
model = AutoModelForCausalLM.from_pretrained("datajuicer/LLaMA-1B-dj-refine-100B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use datajuicer/LLaMA-1B-dj-refine-100B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "datajuicer/LLaMA-1B-dj-refine-100B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "datajuicer/LLaMA-1B-dj-refine-100B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/datajuicer/LLaMA-1B-dj-refine-100B

SGLang

How to use datajuicer/LLaMA-1B-dj-refine-100B 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 "datajuicer/LLaMA-1B-dj-refine-100B" \
    --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": "datajuicer/LLaMA-1B-dj-refine-100B",
		"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 "datajuicer/LLaMA-1B-dj-refine-100B" \
        --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": "datajuicer/LLaMA-1B-dj-refine-100B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use datajuicer/LLaMA-1B-dj-refine-100B with Docker Model Runner:
```
docker model run hf.co/datajuicer/LLaMA-1B-dj-refine-100B
```

News

Our first data-centric LLM competition begins! Please visit the competition's official websites, FT-Data Ranker (1B Track, 7B Track), for more information.

Introduction

This is a reference LLM from Data-Juicer.

The model architecture is LLaMA-1.3B and we adopt the OpenLLaMA implementation. The model is pre-trained on 100B tokens of Data-Juicer's refined RedPajama and Pile. It achieves an average score of 33.07 over 16 HELM tasks, beating LLMs trained on original RedPajama and Pile datasets.

For more details, please refer to our paper.

Downloads last month: 15

Datasets used to train datajuicer/LLaMA-1B-dj-refine-100B

Paper for datajuicer/LLaMA-1B-dj-refine-100B

Data-Juicer: A One-Stop Data Processing System for Large Language Models

Paper • 2309.02033 • Published Sep 5, 2023 • 4