gpt-neo topic

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed

Xirider

QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.

geekjr

Fine-Tune EleutherAI GPT-Neo And GPT-J-6B To Generate Netflix Movie Descriptions Using Hugginface And DeepSpeed

dredwardhyde

A repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.

arrmansa

A basic ui for running gpt neo 2.7B on low vram (3 gb Vram minimum)

arrmansa

Create soft prompts for fairseq 13B dense, GPT-J-6B and GPT-Neo-2.7B for free in a Google Colab TPU instance

VE-FORBRYDERNE

Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research

promptslab

SkyCode是一个多语言开源编程大模型，采用GPT3模型结构，支持Java, JavaScript, C, C++, Python, Go, shell等多种主流编程语言，并能理解中文注释。模型可以对代码进行补全，拥有强大解题能力，使您从编程中解放出...

SkyWorkAIGC

Salesforce codegen with web server

git-cloner

Fine-tuning 6-Billion GPT-J (& other models) with LoRA and 8-bit compression

gustavecortal