Lu Cheng, Huan Liu, Anique Tahir
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 fullmodel 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 GPT 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.11366")
get_code_for_paper("2403.11366")
have("2403.11366")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2403.11366.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2403.11366)
Connect an agent — have() is free.