LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report · HackerPapers discussions

LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report — mentioned by w4nderlust

Mon, 01 Jul 2024 20:02:58 GMT

We got very similar findings: we published a paper that show that smaller LLMs (3-7b) when finetuned with LoRA can match or outperform GPT-4 on a variety of tasks (29 out of 31) including classification, summarization, info extraction, "reasoning". https://arxiv.org/abs/2405.00732 (Predibase cofounder and coauthor of the paper)

Paper and discussion history. A mention is not an endorsement.

LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report — HN submission

Wed, 22 May 2024 16:00:35 GMT

LoRA Land: 310 Fine-Tuned LLMs That Rival GPT-4, a Technical Report

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report — HN submission

Fri, 03 May 2024 19:47:14 GMT

LoRA Land: 310 Fine-Tuned LLMs That Rival GPT-4, a Technical Report

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.