Instructions to use umd-zhou-lab/recycled-wizardlm-7b-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use umd-zhou-lab/recycled-wizardlm-7b-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="umd-zhou-lab/recycled-wizardlm-7b-v1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("umd-zhou-lab/recycled-wizardlm-7b-v1.0")
model = AutoModelForMultimodalLM.from_pretrained("umd-zhou-lab/recycled-wizardlm-7b-v1.0")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use umd-zhou-lab/recycled-wizardlm-7b-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "umd-zhou-lab/recycled-wizardlm-7b-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "umd-zhou-lab/recycled-wizardlm-7b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/umd-zhou-lab/recycled-wizardlm-7b-v1.0

SGLang

How to use umd-zhou-lab/recycled-wizardlm-7b-v1.0 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 "umd-zhou-lab/recycled-wizardlm-7b-v1.0" \
    --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": "umd-zhou-lab/recycled-wizardlm-7b-v1.0",
		"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 "umd-zhou-lab/recycled-wizardlm-7b-v1.0" \
        --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": "umd-zhou-lab/recycled-wizardlm-7b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use umd-zhou-lab/recycled-wizardlm-7b-v1.0 with Docker Model Runner:
```
docker model run hf.co/umd-zhou-lab/recycled-wizardlm-7b-v1.0
```

Model Card for umd-zhou-lab/recycled-wizardlm-7b-v1.0

This model is trained by fine-tuning llama-2 with recycled WizardLM(70k) data V1.

Model Details

Model Description

Developed by: UMD Tianyi Zhou Lab
Model type: An auto-regressive language model based on the transformer architecture
License: Llama 2 Community License Agreement
Finetuned from model: meta-llama/Llama-2-7b

Model Sources

GitHub: Reflection-Tuning
Paper: Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning
Data: recycled_wiz70_v1

Uses

The primary use of this model is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.

Training

We use the prompt from FastChat:

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am ...</s>......

Hyperparameter	Global Batch Size	Learning rate	Epochs	Max length	Weight decay	Warmup Rate
Recycled Models (7B)	128	2e-5	3	2048	0	0.03

Performance

The following table provides a comparison between our recycled models (V1) and baseline models on the AlpacaEval Leaderboard and Huggingface Open LLM Leaderboard.

The Recycled Alpaca Data can be found here: [hf-Link]
The Recycled WizardLM (70k) Data can be found here: [hf-Link]

	AlpacaEval	Avg	ARC	HellaSwag	MMLU	TruthfulQA	Model
Alpaca 7B	26.46	50.21	42.65	76.91	41.73	39.55	/
Recycled Alpaca 7B V1.0	76.99	56.18	53.92	77.68	47.55	45.55	[hf-Link]
Recycled Alpaca 13B V1.0	83.42	58.93	58.70	80.80	53.11	43.12	[Link]

WizardLM 7B	67.64	54.18	51.60	77.70	42.70	44.70	/
Recycled WizardLM 7B V1.0	78.88	56.21	53.92	77.05	48.35	45.52	[hf-Link]

Citation

Please consider citing our paper if you think our codes, data, or models are useful. Thank you!

@misc{li2023reflectiontuning,
      title={Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning}, 
      author={Ming Li and Lichang Chen and Jiuhai Chen and Shwai He and Heng Huang and Jiuxiang Gu and Tianyi Zhou},
      year={2023},
      eprint={2310.11716},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Downloads last month: 9

Dataset used to train umd-zhou-lab/recycled-wizardlm-7b-v1.0

Paper for umd-zhou-lab/recycled-wizardlm-7b-v1.0

Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning

Paper • 2310.11716 • Published Oct 18, 2023 • 6