Fine-tuning AND Prompting/In-context learning
Descendants partagés
10 Documents
How many Labelled Examples do you need for a BERT-sized Model to Beat GPT-4 on Predictive Tasks? - Speaker Deck
Tags:
2023-10-27 A propos
Leandro von Werra sur X : "Companies are currently deciding whether to invest in fine-tuning their own open LLMs (e.g. Llama 2) or to use closed LLMs via an API (e.g. Claude or GPT4)..."
Tags:
2023-10-01 A propos
[2309.12307] LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
Tags:
2023-09-26 A propos
Why You (Probably) Don't Need to Fine-tune an LLM - Tidepool by Aquarium
Tags:
2023-08-19 A propos
Rachel Woods sur X : "There's a resurgence of interest in fine tuning LLMs I've yet to see a successful public use case where fine tuning > prompting. But here's where I see fine tuning *mattering*..."
Tags:
2023-08-19 A propos
[2306.07536] TART: A plug-and-play Transformer module for task-agnostic reasoning
Tags:
2023-06-15 A propos
Andrej Karpathy sur Twitter : "There's a chance that LoRA finetunes work so well that it dramatically alters the finetuning vs. retrieval + few-shot prompting power dynamic..."
Tags:
2023-04-21 A propos
Prompting, Instruction Finetuning, and RLHF (CS224N)
Tags:
2023-02-16 A propos
[2205.05638] Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
Tags:
2022-12-15 A propos
How many data points is a prompt worth?
Tags:
2021-04-08 A propos