umd-zhou-lab/recycled-alpaca-7b-v1.0
umd-zhou-lab/recycled-alpaca-7b-v1.0 is a 7 billion parameter auto-regressive language model developed by UMD Tianyi Zhou Lab. It is fine-tuned from Llama-2-7b using a novel 'recycled alpaca data V1' dataset, demonstrating significant performance improvements on benchmarks like AlpacaEval and MMLU compared to its base model. This model is primarily intended for research in large language models and chatbots, focusing on the impact of data recycling on instruction-tuning.
Loading preview...
Model Overview
umd-zhou-lab/recycled-alpaca-7b-v1.0 is a 7 billion parameter instruction-tuned language model developed by the UMD Tianyi Zhou Lab. It is based on the Llama-2-7b architecture and utilizes a unique "recycled alpaca data V1" dataset for fine-tuning, as detailed in their paper, "Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning." This approach aims to enhance instruction-following capabilities through efficient data utilization.
Key Capabilities & Performance
This model demonstrates notable performance gains over its base Llama-2-7b model, particularly in instruction-following tasks. Key performance metrics include:
- AlpacaEval: Achieves 76.99, a substantial improvement over the 26.46 scored by the original Alpaca 7B.
- MMLU: Scores 47.55, outperforming the 41.73 of Alpaca 7B.
- Overall Average: Shows an average score of 56.18 across various benchmarks, including ARC and HellaSwag.
Training Details
The model was trained with a global batch size of 128, a learning rate of 2e-5, and 3 epochs, using a maximum sequence length of 2048. The training utilized prompts from FastChat. The recycled Alpaca data used for fine-tuning is publicly available.
Intended Use Cases
- Research: Ideal for researchers studying large language models, instruction-tuning, and data efficiency.
- Chatbot Development: Suitable for hobbyists and researchers exploring advanced chatbot functionalities.
Citation
If you use this model, please cite the associated paper: Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning.