Semanlink - Continued pre-training

RDF

Printer friendly

Search Tag:

Search Doc:

Preferences...

Tag Cloud

AI on consumer hardware - Catastrophic forgetting - Jeremy Howard - LLama3 - Parameter-efficient fine-tuning (PEFT) - Quantization - Task-specific models - Twitter thread -

Parents:

LM Fine-tuning

Continued pre-training

Related Tags:

Descendants

2 Documents (Long List)

Jeremy Howard sur X : "FSDP/QDoRA with Llama3 : I believe that this combination is likely to create better task-specific models than anything else at any cost."

Tags:

2024-04-23 About

The End of Finetuning — with Jeremy Howard of Fast.ai

Tags:

2023-10-20 About

Properties

sl:creationDate : 2024-04-23
sl:creationTime : 2024-04-23T22:39:20Z
rdf:type : sl:Tag
skos:prefLabel : Continued pre-training