Dave Spector's repositories
ZeitSatTrack
A Satellite Tracking Library for Swift
attention_with_linear_biases
Code for the ALiBi method for transformer language models (ICLR 2022)
alpaca.cpp
Locally run an Instruction-Tuned Chat-Style LLM
camel
🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
dmmiller612-bert-extractive-summarizer
Easy to use extractive text summarization with BERT
dolly
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
Facebookresearch-llama
Inference code for LLaMA models
gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
huggingface-notebooks
Notebooks using the Hugging Face libraries 🤗
huggingface-transformer-course
The Hugging Face course on Transformers
hwchase17-langchain
⚡ Building applications with LLMs through composability ⚡
LAION-AI-blade2blade
Adversarial Training and SFT for Bot Safety Models
LAION-AI-Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
LLMsPracticalGuide
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)
mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
Microsoft-JARVIS
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
Microsoft-semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
milvus
A cloud-native vector database, storage for next generation AI applications
MineDojo
Building Open-Ended Embodied Agents with Internet-Scale Knowledge
reworkd-AgentGPT
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
Significant-Gravitas-Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
StabilityAI-StableLM
StableLM: Stability AI Language Models
weaviate
Weaviate is an open source vector database 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.