Open source, high performance fine tuning as a service for GPT4 quality models with 5x lower latency and 3x lower cost.
Directory
Search results
Published directory entries matching your search.
Practical Tips for Finetuning LLMs Using LoRA (Low-Rank Adaptation) provides machine-learning models, research, training resources, or evaluation…
Optimized Stable Diffusion modified to run on lower GPU VRAM.
An awesome list of low- and no-code generative AI resources.
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Gestell studies PTX, SASS, compiler lowering, and GPU execution behavior.
Fast and convenient feature processing for low latency machine learning in Go.
A header-only C++11 Neural Network library. Low dependency, native traditional chinese document.
Using Low-rank adaptation to quickly fine-tune diffusion models.
A low-code framework for building custom AI models like LLMs and other deep neural networks. opensource.
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"s.
A low-level Linear Regression Engine utilizing the Ordinary Least Squares (OLS) method and QR decomposition.
An open-source coding agent built for low-cost and open-weight models.
Open-source, low-code machine learning library in Python that automates machine learning workflows.
An offline speech recognition toolkit with C++ support, designed for low-resource devices and multiple languages.
Godot 4.x asset that enables NPCs to interact with players using local LLMs for structured, offline-first learning conversations in games.
Create playable games with AI prompts. Describe your idea or choose a template, then build and deploy your game. No coding required.
"AI for Good" Campaigns Are the Wrong Approach - IEEE Spectrum provides machine-learning models, research, training resources, or evaluation tools.
Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai.
A genomics processing engine and specialized file format built using Apache Avro, Apache Spark and Parquet. Apache 2 licensed.
BlockAGI conducts iterative, domain-specific research, and outputs detailed narrative reports to showcase its findings.
Specialized AI Analysis of Congressional Stock Trades. Track the real-time stock trades of every member of Congress, aggregated into a single.
Copysmith builds Frase, Describely, and Rytr — specialized AI platforms helping brands rank in search, get cited by AI, and scale content.
Framework for orchestrating teams of specialized AI agents. Role-based agents collaborate on complex tasks. $20M+ in VC funding. Apache-2.0.