Ideas & society2023 · shared on Hacker News
QLoRA: Efficient Finetuning of Quantized LLMs
Explore QLoRA: Efficient Finetuning of Quantized LLMs, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ywolecki ·
LoRA Learns Less and Forgets Less
177 points60 comments
Yignoramous ·
Guide to Fine-Tuning LLMs
157 points16 comments
YsurrTurr ·
Ask HN: What's the best self hosted/local alternative to GPT-4?
115 points61 comments
Ylebek ·
The False Promise of Imitating Proprietary LLMs
18 points5 comments
Yjustusmattern ·
Show HN: Haven (YC S23) – Quickly iterate when fine-tuning open-source LLMs
11 points0 comments
YMacsHeadroom ·
QLoRA: Efficient Finetuning of Quantized LLMs
2 points1 comments
Yconvexstrictly ·
Falcon 40B LLM (which beats Llama) now Apache 2.0
2 points1 comments
Ydanielhanchen ·
80% faster, 50% less memory, 0% loss of accuracy Llama finetuning
2 points1 comments
Ymatt_d ·
TorchLean: Formalizing Neural Networks in Lean
2 points0 comments
YGarcia98 ·
QLoRA: Efficient Finetuning of Quantized LLMs
1 points0 comments