Instructions to use datajuicer/LLaMA2-7B-ZH-Chat-52k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use datajuicer/LLaMA2-7B-ZH-Chat-52k with Transformers:

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

pipe = pipeline("text-generation", model="datajuicer/LLaMA2-7B-ZH-Chat-52k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("datajuicer/LLaMA2-7B-ZH-Chat-52k")
model = AutoModelForCausalLM.from_pretrained("datajuicer/LLaMA2-7B-ZH-Chat-52k")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use datajuicer/LLaMA2-7B-ZH-Chat-52k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "datajuicer/LLaMA2-7B-ZH-Chat-52k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "datajuicer/LLaMA2-7B-ZH-Chat-52k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/datajuicer/LLaMA2-7B-ZH-Chat-52k

SGLang

How to use datajuicer/LLaMA2-7B-ZH-Chat-52k 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/LLaMA2-7B-ZH-Chat-52k" \
    --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/LLaMA2-7B-ZH-Chat-52k",
		"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/LLaMA2-7B-ZH-Chat-52k" \
        --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/LLaMA2-7B-ZH-Chat-52k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use datajuicer/LLaMA2-7B-ZH-Chat-52k with Docker Model Runner:
```
docker model run hf.co/datajuicer/LLaMA2-7B-ZH-Chat-52k
```

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 LLaMA2-7B and we built it upon the a pre-trained Chinese checkpoint from FlagAlpha. The model is fine-trained on 52k Chinese chat samples of Data-Juicer's refined alpaca-CoT data. It beats LLaMA2-7B fine-tuned on 543k Belle samples in GPT-4 evaluation.

For more details, please refer to our paper.

Downloads last month: 8

Dataset used to train datajuicer/LLaMA2-7B-ZH-Chat-52k

Paper for datajuicer/LLaMA2-7B-ZH-Chat-52k

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

Paper • 2309.02033 • Published Sep 5, 2023 • 4