Jaromír's starred repositories
haystack
:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
LLMsPracticalGuide
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Drive-Backup
Python script to backup your Google Drive to your computer or a backup hard drive.
humble-steam-key-redeemer
Python script to extract all Humble Bundle keys and redeem them on Steam automagically.
PEER-CVPR23
Authors' implementation of PEER
oracle-sage
This repository contains the code for the paper "Oracle-SAGE: planning ahead in graph-based deep reinforcement learning" by Chester, Dann, Zambetta, and Thangarajah published at ECML/PKDD 2022.
unlimiformer
Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
Stable-Diffusion-Latent-Space-Explorer
Codebase for performing various experiments with Stable Diffusion, supported by the diffusers library.