Lucas Hänke de Cansino's repositories
metavoice-src
AI for human-level speech intelligence
Agentless
Agentless🐱: an agentless approach to automatically solve software development problems
AutoArch
Automated Arch Linux Install
chroma
the AI-native open-source embedding database
dora
Implementation of DoRA
dspy
DSPy: The framework for programming—not prompting—foundation models
entity-recognition-datasets
A collection of corpora for named entity recognition (NER) and entity recognition tasks. These annotated datasets cover a variety of languages, domains and entity types.
functionary
Chat language model that can use tools and interpret the results
generative-models
Generative Models by Stability AI
go-chroma
Go port of Chroma vector storage
godot4-ai-npc-example
A Godot 4 Artificial Intelligence (AI) NPC example project.
laserRMT
This is our own implementation of 'Layer Selective Rank Reduction'
LocalAI
:robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs ggml, gguf, GPTQ, onnx, TF compatible models: llama, llama2, rwkv, whisper, vicuna, koala, cerebras, falcon, dolly, starcoder, and many others
multinerd
Repository for the paper "MultiNERD: A Multilingual, Multi-Genre and Fine-Grained Dataset for Named Entity Recognition (and Disambiguation)" (NAACL 2022).
next-auth
Authentication for the Web.
outlines
Structured Text Generation
Real-Time-Latent-Consistency-Model
Demo showcasing ~real-time Latent Consistency Model pipeline with Diffusers and a MJPEG stream server
SparsePrimingRepresentations
Public repo to document some SPR stuff
tennis_analysis
This project analyzes Tennis players in a video to measure their speed, ball shot speed and number of shots. This project will detect players and the tennis ball using YOLO and also utilizes CNNs to extract court keypoints. This hands on project is perfect for polishing your machine learning, and computer vision skills.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
trl
Train transformer language models with reinforcement learning.
unsloth
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory