--- 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](https://huggingface.co/meta-llama/Llama-2-7b) ### Model Sources - **GitHub:** [Reflection-Tuning](https://github.com/tianyi-lab/Reflection_Tuning) - **Paper:** [Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning](https://arxiv.org/abs/2310.11716) - **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](https://github.com/lm-sys/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.USER: Who are you? ASSISTANT: I am ......... ``` | 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]](https://huggingface.co/umd-zhou-lab/recycled-alpaca-7b-v2.0)| ||||||||||| | **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]](https://huggingface.co/umd-zhou-lab/recycled-wizardlm-7b-v2.0)| ||||||||| ## 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](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_umd-zhou-lab__recycled-wizardlm-7b-v2.0) | 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|