Vector search demo with the arXiv paper dataset, HuggingFace, OpenAI, FastAPI, React, and Redis as the vector database.

https://github.com/RedisVentures/redis-arXiv-search
https://docsearch.redisventures.com/

​​LLaMA: Open and Efficient Foundation Language Models

LLaMA is a set of large language models, ranging from 7B to 65B parameters, that have been trained on publicly available datasets containing trillions of tokens. The LLaMA-13B model performs better than GPT-3 (175B) on most benchmarks, and the LLaMA-65B model is competitive with other state-of-the-art models, such as Chinchilla70B and PaLM-540B. This suggests that it is possible to achieve excellent performance in language modeling without relying on proprietary or inaccessible datasets.

Paper: https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/

Code: https://github.com/facebookresearch/llama

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-llama

#deeplearning #nlp #transformer #sota #languagemodel

Open source implementation for LLaMA-based ChatGPT training process. Faster and cheaper training than ChatGPT (wip)

https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama

Prompt Engineering Guide

https://github.com/dair-ai/Prompt-Engineering-Guide

xFormers - Toolbox to Accelerate Research on Transformers

xFormers is: Customizable building blocks: Independent/customizable building blocks that can be used without boilerplate code. The components are domain-agnostic and xFormers is used by researchers in vision, NLP and more.

Research first: xFormers contains bleeding-edge components, that are not yet available in mainstream libraries like pytorch.

Built with efficiency in mind: Because speed of iteration matters, components are as fast and memory-efficient as possible. xFormers contains its own CUDA kernels, but dispatches to other libraries when relevant.


https://github.com/facebookresearch/xformers

🤗 Diffusers provides pretrained diffusion models across multiple modalities, such as vision and audio, and serves as a modular toolbox for inference and training of diffusion models.

https://github.com/huggingface/diffusers/tree/main/examples/community#magic-mix

InvokeAI: A Stable Diffusion Toolkit

https://github.com/invoke-ai/InvokeAI

Visual ChatGPT (🔥 Score: 152+ in 2 hours)

Link: https://readhacker.news/s/5zPu5
Comments: https://readhacker.news/c/5zPu5

Вот эта "неидеальность" со временем уйдёт, а мне так даже заходит больше. А ведь раньше гличи были на пике трендов.

Если хотите погонять свою видяху для создания Multi-frame Video rendering for SD, то вам вот за этой тулзовиной.

GPT-4 Developer Livestream
https://www.youtube.com/watch?v=outcGtbnMuQ

ModelScope Text-2-Video: Китайский опенсоурс разродился открытой моделькой для генерации видео по тексту

Это первая диффузионная text2video модель с открытым кодом и опуьликованными весами (1.7 млрд параметров).

Отдельный респект идет Шаттерстоку, данные с которого по всей видимотси использовались для тренировки модели 😂.

Чтобы запустить локально потребуется 16 GB RAM и 16 GB VRAM: инструкция. Пока генерит видео только 256x256.

Ну что, давайте побыстрее заполним интернет проклятыми видео!

Demo
Model weights

@ai_newz