Birbal: An efficient 7B instruct-model fine-tuned with curated datasets
Keywords: Data Curation, LLM Efficiency, Instruction Tuning, QLoRA
TL;DR: System description paper of data curation for NeurIPS LLM Efficiency Challenge winning submission
Abstract: LLMOps incur significant costs due to hardware requirements, hindering their widespread accessibility. Additionally, a lack of transparency in model training methods and data contributes to the majority of models being non-reproducible. To tackle these challenges, the LLM Efficiency Challenge was introduced at NeurIPS Workshop1, aiming to adapt foundation models on a diverse set of tasks via fine-tuning on a single GPU (RTX 4090 or A100 with 40GB) within a 24-hour timeframe. In this system description paper, we introduce Birbal, our Mistral-7B based winning model, fine-tuned on a single RTX 4090 for 16 hours. Birbal’s success lies in curating high-quality instructions covering diverse tasks, resulting in a 35% performance improvement over second-best Qwen-14B based submission.
Primary Subject Area: Role of data in foundation models: pre-training, prompting, fine-tuning
Paper Type: Research paper: up to 8 pages
Participation Mode: Virtual
Confirmation: I have read and agree with the workshop's policy on behalf of myself and my co-authors.
Submission Number: 56
Loading