큰 언어 모델을 협력하여 실행하는 오픈 소스 도구
1. 모델의 작은 부분을 로드하세요 2. 다른 사람들과 협력하여 나머지 부분을 제공하세요 3. 추론 또는 세부 조정을 실행하세요
작성자: Tanish Chowdhary 님의 글 5월 20 2024
인공지능의 미래를 열다: 대형 언어 모델에 의한 6가지 놀라운 변화 발견하기!
작성자: Tejal Sushir 님의 글 5월 22 2024
미래를 해제하세요: MLLM 기술이 AI 상호 작용을 혁신적으로 변화시키는 11가지 방법을 발견하세요!
작성자: Eleanor 님의 글 3월 31 2024
Toolify AI와 함께 세상을 혁신하는 최첨단 AI 모델을 발견하세요. 오늘 미래를 탐험해보세요!
소셜 리스닝
AI Face Detection on Local Machine Using InsightFace
This video gives demo of InsightFace which is an AI library for 2D and 3D face analysis. It offers optimized algorithms for face recognition, detection, and alignment. #insightface PLEASE FOLLOW ME: ▶ LinkedIn: https://www.linkedin.com/in/fahdmirza/ ▶ YouTube: https://www.youtube.com/@fahdmirza ▶ Blog: https://www.fahdmirza.com RELATED VIDEOS: ▶ Petals https://petals.ml/ or https:petals.dev ▶ GitHub Repo https://github.com/deepinsight/insightface All rights reserved © 2021 Fahd Mirza
Petals - Run Any LLM on Any Device - Distributed LLMs
If you are looking to install and run any LLM on any device, then Petals is the answer. Its like AI torrent which decentralizes the LLMs across the globe. ▶ Step by Step Petals Installation Local https://www.youtube.com/watch?v=gjfUW08uXeY&t=5s #petals PLEASE FOLLOW ME: ▶ LinkedIn: https://www.linkedin.com/in/fahdmirza/ ▶ YouTube: https://www.youtube.com/@fahdmirza ▶ Blog: https://www.fahdmirza.com RELATED VIDEOS: ▶ Prompt Engineering 101 for Beginners https://youtu.be/qN-mUfrgBDk ▶ Introduction to AWS Bedrock https://youtu.be/tvsRAtZZ_Sc ▶ Petals https://petals.ml/ or https:petals.dev ▶ Petals Colab https://colab.research.google.com/drive/1uCphNY7gfAUkdDrTx21dZZwCOUDCMPw8?usp=sharing#scrollTo=1s1IrE1H8wwr All rights reserved © 2021 Fahd Mirza
Demo: BARD AI vs Guanaco-65B LLM (LLama-65B) on PETALS
Compare BARD LLM from Google on its first day in EUROPE vs Guanaco 65B LLM on Petals. Short Demo based on three tasks (live demo). A 65 billion parameter model against the latest LLM from Google. Guanaco 65B is the further optimized model based on LLama 65B (research license only). Optinal you can explore in real-time LLama 65B, BLOOM (165B) or BLOOMZ on Petals. Choose the model you prefer and experience its performance for your specific downstream task. The Guanaco models are open-source finetuned chatbots obtained through 4-bit QLoRA tuning of LLaMA base models on the OASST1 dataset. https://huggingface.co/timdettmers/guanaco-65b (no commercial use allowed by META) PETALS: http://chat.petals.ml/ Colab for Petals: https://colab.research.google.com/drive/1uCphNY7gfAUkdDrTx21dZZwCOUDCMPw8?usp=sharing #bard #guanaco #ai
총 9개의 소셜 미디어 데이터를 보려면 잠금을 해제해야 합니다