Robuta

Sponsor of the Day: Jerkmate
https://huggingface.co/furiosa-ai/Llama-3.3-70B-Instruct furiosa-ai/Llama-3.3-70B-Instruct · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. ai llama 370b instructhugging facefuriosa https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated huihui-ai/Llama-3.2-3B-Instruct-abliterated · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. ai llama 32 3b instructhugging facehuihuiabliterated https://huggingface.co/huihui-ai/Llama-3.3-70B-Instruct-abliterated huihui-ai/Llama-3.3-70B-Instruct-abliterated · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. ai llama 370b instructhugging facehuihuiabliterated https://www.answer.ai/posts/2024-04-26-fsdp-qdora-llama3.html Efficient finetuning of Llama 3 with FSDP QDoRA – Answer.AI We’re releasing FSDP QDoRA, a scalable and memory-efficient method to close the gap between parameter efficient finetuning and full finetuning. llama 3answer aiefficientfinetuningfsdp