chenghuzi
Follow
Stars
Visualisations of data are at the core of every publication of scientific research results. They have to be as clear as possible to facilitate the communication of research. As data can have differ…
A Python package for fast and robust Image Stitching
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
A high-throughput and memory-efficient inference and serving engine for LLMs
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Paper list of multi-agent reinforcement learning (MARL)
Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.
Bicycle: Intervention-Based Causal Discovery with Cycles
awesome papers in LLM interpretability
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
A library for mechanistic interpretability of GPT-style language models
Arrange methods and example on finetune LLMs
A collection of AWESOME things about mixture-of-experts
Structured state space sequence models
A NARS implemented as a GPT model prompted to invoke reasoning steps, with NARS-based memory and control machinery implemented in Python.
A machine learning software for extracting information from scholarly documents
Code for fintune ChatGLM-6b using low-rank adaptation (LoRA)
knowledge repository managed with org-mode and org-roam.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
Persistent/Immutable/Functional data structures for Python
An open-source userscript manager for Safari