unverciftci

nox

Efficient fine-tuning for ko-llm models

pretzelai

Open-source, browser-local data exploration using DuckDB-Wasm and PRQL

DeepSeek-V2

DiscoVery

It is an LLM powered assistant that can read directories, even images, to gather information about companies. You can use HuggingFace or Ollama models,Claude,OpenAI and Google LLMs.I am inspired by IBM Discovery.

markmap

Build mindmaps with plain text

text-splitter

Split text into semantic chunks, up to a desired chunk size. Supports calculating length by characters and tokens, and is callable from Rust and Python.

pdftext

Extract structured text from pdfs quickly

dmesh

Official implementation for "DMesh: A Differentiable Representation for General Meshes".

pratical-llms

A collection of hand on notebook for LLMs practitioner

T-Rex

T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

ViP-LLaVA

[CVPR2024] ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts

GLiNER

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 24

evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

mindgraph

proof of concept prototype for generating and querying against an ever-expanding knowledge graph with ai

RealNet

Offical implementation of "RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection (CVPR 2024)"

continuous-eval

Open-Source Evaluation for GenAI Application Pipelines

chronos-forecasting

Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting

causalai

Salesforce CausalAI Library: A Fast and Scalable framework for Causal Analysis of Time Series and Tabular Data

TripoSR

DeLLMa

Official Implementation of "DeLLMa: A Framework for Decision Making Under Uncertainty with Large Language Models"

LDNets

ComfyUI-Launcher

Run any ComfyUI workflow w/ ZERO setup.

tinyBenchmarks

Evaluating LLMs with fewer examples

wmdp

WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining general capabilities.

Anthropic-Claude-Function-Calling

visualwebarena

VisualWebArena is a benchmark for multimodal agents.

dust3r

DUSt3R: Geometric 3D Vision Made Easy

StructLM

Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding"

Time-Series-Library

A Library for Advanced Deep Time Series Models.

bonito

A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.