Steven Morrey's repositories
AgentGPT
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
AudioGPT
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
CfC
Closed-form Continuous-time Neural Networks
DeBERTa
The implementation of DeBERTa
dedup
Deduplicate files on a linux system by comparing file hashes and replacing duplicated files with symlinks to a common file
eyecite
Find legal citations in any block of text
Freenove_Robot_Dog_Kit_for_Raspberry_Pi
Apply to FNK0050
gpt4all
gpt4all: an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue
hyperDB
A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $35M cap.
langchain
⚡ Building applications with LLMs through composability ⚡
memorizing-transformers-pytorch
Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch
mlc-llm
Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
openai-cookbook
Examples and guides for using the OpenAI API
openlibrary
One webpage for every book ever published!
pyllama
LLaMA: Open and Efficient Foundation Language Models
RECITE
Code of ICLR paper: https://openreview.net/forum?id=-cqvvvb-NkI
safari
Convolutions for Sequence Modeling
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
telepathic-element
Telepathic Element is a templated web component and serves as the base class for telepathy
telepathic-loader
TelepathicLoader is an ES6 class that kicks off loading of templates and subtemplates for telepathy based projects, just make sure your element ends in -element
tfjs-examples
Examples built with TensorFlow.js
tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
weaviate
Weaviate is an open source vector search engine that stores both objects and vectors, allowing for combining vector search with structured filtering with the fault-tolerance and scalability of a cloud-native database, all accessible through GraphQL, REST, and various language clients.
web-llm
Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.