Instructions to use datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B with Transformers:

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

pipe = pipeline("text-generation", model="datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B")
model = AutoModelForCausalLM.from_pretrained("datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B 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-150B-instruct-4.7B"
# 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-150B-instruct-4.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B

SGLang

How to use datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B 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-150B-instruct-4.7B" \
    --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-150B-instruct-4.7B",
		"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-150B-instruct-4.7B" \
        --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-150B-instruct-4.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B with Docker Model Runner:
```
docker model run hf.co/datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B
```

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 150B tokens of Data-Juicer's refined RedPajama and Pile, and 4.7B tokens of Data-Juicer refined instruct data. It achieves an average score of 36.76 over 16 HELM tasks, improved the OpenLLaMA-DJ-150B by 2.55 point.

For more details, please refer to our paper.

Downloads last month: 21

Datasets used to train datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B

Paper for datajuicer/LLaMA-1B-dj-refine-150B-instruct-4.7B

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

Paper • 2309.02033 • Published Sep 5, 2023 • 4