Pith. sign in

REVIEW 1 cited by

JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.11366 v2 pith:TUMMT23L submitted 2024-03-17 cs.LG cs.CLcs.DC

classification cs.LGcs.CLcs.DC
keywords fine-tuningaugmentedefficientframeworkgpusllmsmemorymodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The scaling of Large Language Models (LLMs) for retrieval-based tasks, particularly in Retrieval Augmented Generation (RAG), faces significant memory constraints, especially when fine-tuning extensive prompt sequences. Current open-source libraries support full-model inference and fine-tuning across multiple GPUs but fall short of accommodating the efficient parameter distribution required for retrieved context. Addressing this gap, we introduce a novel framework for PEFT-compatible fine-tuning of Llama-2 models, leveraging distributed training. Our framework uniquely utilizes JAX's just-in-time (JIT) compilation and tensor-sharding for efficient resource management, thereby enabling accelerated fine-tuning with reduced memory requirements. This advancement significantly improves the scalability and feasibility of fine-tuning LLMs for complex RAG applications, even on systems with limited GPU resources. Our experiments show more than 12x improvement in runtime compared to Hugging Face/DeepSpeed implementation with four GPUs while consuming less than half the VRAM per GPU.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Evaluating LLMs Capabilities Towards Understanding Social Dynamics

    cs.LG 2024-11 conditional novelty 5.0 of 10

    LLMs show improved directionality detection after fine-tuning but perform near chance at cyberbullying and anti-bullying classification, pointing to weak semantic understanding of informal social media language.

Pith tools