README.md

metadata

language:
  - en
license: llama2
model-index:
  - name: recycled-wizardlm-7b-v2.0
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 54.95
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=umd-zhou-lab/recycled-wizardlm-7b-v2.0
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 77.85
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=umd-zhou-lab/recycled-wizardlm-7b-v2.0
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 45.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=umd-zhou-lab/recycled-wizardlm-7b-v2.0
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 48.29
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=umd-zhou-lab/recycled-wizardlm-7b-v2.0
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 71.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=umd-zhou-lab/recycled-wizardlm-7b-v2.0
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 12.36
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=umd-zhou-lab/recycled-wizardlm-7b-v2.0
          name: Open LLM Leaderboard

Model Card for umd-zhou-lab/recycled-wizardlm-7b-v2.0

This model is trained by fine-tuning llama-2 with recycled WizardLM(70k) data V2.

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: Coming soon

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 (V2) and baseline models on the AlpacaEval Leaderboard and Huggingface Open LLM Leaderboard.

The V2 Recycled Alpaca Data and WizardLM data, and the corresponding paper will be released soon.

	AlpacaEval		Avg	ARC	HellaSwag	MMLU	TruthfulQA		Model
Alpaca 7B	26.46		50.21	42.65	76.91	41.73	39.55		/
Recycled Alpaca 7B V2.0	79.58		56.05	54.01	78.07	46.69	45.41		[hf-Link]
WizardLM 7B	67.64		54.18	51.60	77.70	42.70	44.70		/
Recycled WizardLM 7B V2.0	83.48		56.79	54.78	77.86	45.63	48.91		[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}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	51.79
AI2 Reasoning Challenge (25-Shot)	54.95
HellaSwag (10-Shot)	77.85
MMLU (5-Shot)	45.79
TruthfulQA (0-shot)	48.29
Winogrande (5-shot)	71.51
GSM8k (5-shot)	12.36