benhoyle
UK and European Patent Attorney specialising in patents & designs for high-tech industries. Also an Information Engineer.
Hoyle IP Services LimitedBath
benhoyle's Stars
hkproj/pytorch-llama
LLaMA 2 implemented from scratch in PyTorch
ltdrdata/ComfyUI-Manager
ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, this extension provides a hub feature and convenience functions to access a wide range of information within ComfyUI.
AnswerDotAI/RAGatouille
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
anonymousz97/colbertZaloAI
Zalo AI Challenge Legal search using Colbert (around 0.65 F2)
ngshya/easyRAG
Build your own RAG and run it locally on your laptop: ColBERT + DSPy + Streamlit
dmuth/evernote-to-obsidian
Wrapper for the Yarle app to make converting Evernote notebooks to Markdown easier
akosbalasko/yarle
Yarle - The ultimate converter of Evernote notes to Markdown
OpenCodeInterpreter/OpenCodeInterpreter
OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.
charlax/professional-programming
A collection of learning resources for curious software engineers
varunshenoy/super-json-mode
Low latency JSON generation using LLMs ⚡️
python-semantic-release/python-semantic-release
Automating Releases via SemVer and Commit Message Conventions
semantic-release/semantic-release
:package::rocket: Fully automated version management and package publishing
babycommando/machinascript-for-robots
Build LLM-powered robots in your garage with MachinaScript For Robots!
lucidrains/self-rewarding-lm-pytorch
Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI
harshitsinghai77/server-sent-events-using-fastapi-and-reactjs
Server-Sent Events using FastAPI, Starlette, and ReactJS.
luca-medeiros/lang-segment-anything
SAM with text prompt
google-research/scenic
Scenic: A Jax Library for Computer Vision Research and Beyond
astral-sh/ruff
An extremely fast Python linter and code formatter, written in Rust.
VikParuchuri/surya
OCR, layout analysis, reading order, table recognition in 90+ languages
katanaml/sparrow
Data processing with ML, LLM and Vision LLM
Technologicat/pyan
Static call graph generator. The official Python 3 version. Development repo.
davidfraser/pyan
pyan is a Python module that performs static analysis of Python code to determine a call dependency graph between functions and methods. This is different from running the code and seeing which functions are called and how often; there are various tools that will generate a call graph in that way, usually using debugger or profiling trace hooks - for example: https://pycallgraph.readthedocs.org/ This code was originally written by Edmund Horner, and then modified by Juha Jeronen. See README for the original blog posts and links to their repositories.
NVIDIA/ChatRTX
A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM
menyifang/En3D
Official implementation of "En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data", CVPR 2024; 3D Avatar Generation and Animation
natolambert/blogcaster
Python tools for easily translating your blog content to podcasts & YouTube
ali-vilab/AnyDoor
Official implementations for paper: Anydoor: zero-shot object-level image customization
HumanAIGC/OutfitAnyone
Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person
luciddreamer-cvlab/LucidDreamer
Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".
webstorms/Blocks
A new model for quickly training and simulating adaptive leaky integrate-and-fire spiking neural networks.
SqueezeAILab/LLMCompiler
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling