Announcing LoRAX v0.2 Sparse SGMV: vectorize LoRA and base model requests in same batch Tensor Parallel SGMV: multi-GPU, multi-LoRA vectorized inference ExLlama v2 kernels for faster GPT-Q (thanks Florian Zimmermeister!)
…and more! https://
pbase.ai/3T2Nemt
OPEN SOURCE
-
LoRAX v0.2: Sparse SGMV and Tensor Parallel Inference
By
–
-
EPFL’s Llama-2 Medical Fine-Tuned Model Released
By
–
A version of Llama-2 fine-tuned for medicine from EPFL.
-
Fine-tuning and derivatives of core AI models
By
–
What the situation with derivatives of core models, like fine tunes for example?
-
Keras 3 Release Breaks Python Package Test Suites
By
–
I remember when I first started training deep learning models and my whole twitter timeline was the author of keras tweeting about how no one wants to use pytorch keras 3 came out today and the only reason I heard about it is because it broke one of my python package test suites https://
x.com/fchollet/statu
/fchollet/status/1047570406570307584
… -
Fine-tuning T5 Model on Stack Overflow Questions for Automatic Tagging
By
–
🚀Blog-tastic Tuesdays🚀https://t.co/qhCLiOlguT
— Satya Mallick (@LearnOpenCV) 28 novembre 2023
T5, or Text to Text Transfer Transformer, was a groundbreaking language model from Google that could perform multiple tasks. In this week's article, we fine-tune the T5 model on Stack Overflow questions for automatic tag… pic.twitter.com/Q552FyhfpoBlog-tastic Tuesdays https://
learnopencv.com/fine-tuning-t5/ T5, or Text to Text Transfer Transformer, was a groundbreaking language model from Google that could perform multiple tasks. In this week's article, we fine-tune the T5 model on Stack Overflow questions for automatic tag -
Stable Video Diffusion Model by Stability AI Explained
By
–
Good morning fellow AI enthusiast! This week's iteration focuses on the new Stable Diffusion model by @StabilityAI
! It is an open-source video generation model based on the stable diffusion architecture for videos. We dive into how it works https://
open.substack.com/pub/louisbouch
ard/p/stable-video-diffusion-svd-explained?r=25qlky&utm_campaign=post&utm_medium=web
… -
Hardening Open Source Code with OpenSSF at Tokyo Summit
By
–
Boarding flight for Tokyo, Japan I am going to attend @openssf Day and @linuxfoundation Open Source Summit in next few days. I am going to speak about “How to harden up your Open Source code using OpenSSF” Let’s meet if you’re there.
-
Open-source LLMs: Smaller, faster, cheaper alternatives to commercial models
By
–
Open-source LLMs like #Llama2 are smaller, faster & cheaper than commercial #LLMs like @OpenAI #GPT4 — and best of all, when fine-tuned they can deliver equivalent if not better performance Join our webinar to learn how you can get started #finetuning. https://
pbase.ai/49RLm6a -
Local RAG with Qdrant, Ollama, LangChain and LangServe
By
–
Fully Local RAG with Qdrant, Ollama, LangChain and LangServe We're seeing more & more interest in local RAG, and as such we're excited to share a great walkthrough from Data Drifters Uses @qdrant_engine & @Ollama_ai to do this all locally Blog: https://
medium.com/@datadrifters/
fully-local-rag-with-qdrant-ollama-langchain-and-langserve-10d4dd1facbc
… -
GPT-4 ArXiv Paper Assistant Bot for Personalized Research
By
–
tatsu-lab/gpt_paper_assistant: GPT4 based personalized ArXiv paper assistant bot https://
bit.ly/3uysUPI #AI #MachineLearning #DeepLearning #LLMs #DataScience