Name: Dave Spector
Type: User
Company: @TheZeitgeist (Zeitgeist Information Systems, LLC)
Bio: Engineer/Writer in DevPubs @ • IoT maker • foodie • coffee snob/roaster • A New Yorker in SF • W2DHM
Twitter: dhmspector
Location: San Francisco, CA
Blog: http://www.zeitgeist.com/
Dave Spector's Projects
Locally run an Instruction-Tuned Chat-Style LLM
Code for the ALiBi method for transformer language models (ICLR 2022)
🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
the AI-native open-source embedding database
Easy to use extractive text summarization with BERT
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
Inference code for LLaMA models
A library for efficient similarity search and clustering of dense vectors.
Fast and memory-efficient exact attention
Drag & drop UI to build your customized LLM flow using LangchainJS
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
gpt4all: an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue
API to the GPT4All Datalake
GPX parser
Create UIs for your machine learning model in Python in 3 minutes
Notebooks using the Hugging Face libraries 🤗
The Hugging Face course on Transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
⚡ Building applications with LLMs through composability ⚡
Interact privately with your documents using the power of GPT, 100% privately, no data leaks
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
Adversarial Training and SFT for Bot Safety Models
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.