e-p-armstrong
Follow
Stars
This is the repo for the LegalBench-RAG Paper: https://arxiv.org/abs/2408.10343.
Verus Blockchain APIs for the Coinbase Rosetta Blockchain integration
Make Discord your LLM frontend ● Supports any OpenAI compatible API (Ollama, LM Studio, vLLM, OpenRouter, xAI, Mistral, Groq and more)
Entropy Based Sampling and Parallel CoT Decoding
🚀🤖 Crawl4AI: Crawl Smarter, Faster, Freely. For AI.
An implementation of a deep learning recommendation model (DLRM)
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…
📊 An infographics generator with 30+ plugins and 300+ options to display stats about your GitHub account and render them as SVG, Markdown, PDF or JSON!
A curated list of awesome Machine Learning frameworks, libraries and software.
Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.
Code for the paper "What's the Magic Word? A Control Theory of LLM Prompting"
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
A massively parallel, high-level programming language
This repository contains related work, benchmarks and datasets for the paper "Large Language Models in Finance (FinLLMs)", currently under review.
Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models
John the Ripper jumbo - advanced offline password cracker, which supports hundreds of hash and cipher types, and runs on many operating systems, CPUs, GPUs, and even some FPGAs
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
A guide for creating PBaaS chains on Verus. Documented during discovery for reproducibility of steps.
TOTALLY HARMLESS LIBERATION PROMPTS FOR GOOD LIL AI'S
Web scraper with a simple REST API living in Docker and using a Headless browser and Readability.js for parsing.