Anton Polishko's repositories
amazon-sagemaker-generativeai
Repository for training and deploying Generative AI models, including text-text, text-to-image generation and prompt engineering playground using SageMaker Studio.
antp-containers
collection of container related repos
chatarena
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
everythingdata
Ask your data with natural language about anything, get back answers with explanation or SQL queries to do verification of results.
exllama
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
google-datalabs-notebooks
Google Cloud Datalab samples and documentation
google-research
Google Research
honest_llama
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
kickstart.nvim
A launch point for your personal nvim configuration
llama-recipes
Examples and recipes for Llama 2 model
lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
LMFlow
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
local-colab
repo to build local runtime for colab.research.google.com
ludwig
Low-code framework for building custom LLMs, neural networks, and other AI models
ollama-webui
ChatGPT-Style Web UI Client for Ollama 🦙
pybind11_protobuf
Pybind11 bindings for Google's Protocol Buffers
rustlings
:crab: Small exercises to get you used to reading and writing Rust code!
streamlit-example
Example Streamlit app that you can fork to test out share.streamlit.io
super-slack
Run Superagent Workflows from Slack
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
VLM-browser
Large Action Model framework to automate browser interaction