Tag: LLM fine-tuning
Browse our exclusive articles!
Fine-Tuning LLMs with Synthetic Data for Gaming Toxicity
Discover how synthetic data boosts large language models for multi-class toxicity detection in gaming chat, improving moderation and online safety.
AdaMeZO: Memory-Efficient Adam-Style Optimizer for LLMs
Discover AdaMeZO, an Adam-style zeroth-order optimizer that fine-tunes large language models efficiently without storing moment estimates.
RoundPipe: Efficient Multi-GPU Training on Consumer GPUs
Boost large model training efficiency on consumer GPUs with RoundPipe's dynamic pipeline parallelism and optimized scheduling. Open-source and scalable.
TLPO: Boosting Language Consistency in Large Language Models
Discover how Token-Level Policy Optimization (TLPO) reduces language confusion in large language models, improving multilingual accuracy and performance.
LARS: Memory-Efficient Fine-Tuning for On-Device LLMs
Discover how LARS reduces memory use in fine-tuning large language models on devices with limited resources, boosting efficiency without performance loss.