Glavin001

atom-beautify

:mega: Help Wanted - Looking for Maintainer: https://github.com/Glavin001/atom-beautify/issues/2572 | :lipstick: Universal beautification package for Atom editor (:warning: Currently migrating to https://github.com/Unibeautify/ and have very limited bandwidth for Atom-Beautify Issues. Thank you for your patience and understanding :heart: )

Data2AITextbook

🚀 Automatically convert unstructured data into a high-quality 'textbook' format, optimized for fine-tuning Large Language Models (LLMs)

AgentML

Agent Markup Languages for AI Agents

Expertise-by-AI

Learn & build: Always available expertise powered by AI

llm-trainer

Training/Fine-Tuning Large Language Models

h2o-llmstudio

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs

axolotl

Go ahead and axolotl questions

axolotl-cloud

Cauldron

Engine of Evolution: Transforming Ideas into Reality

cog-exllama

Inference using exllama with cog.

colorspace

assign color hues to a collection of text fragments based on embeddings

COQAR

a corpus containing 4.5K conversations from the Conversational Question-Answering dataset CoQA, for a total of 53K follow-up question-answer pairs, in which each original question was manually annotated with at least 2 and at most 3 out-of-context rewritings

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

enhanced-llm-reasoning-tree-of-thoughts

Collection of Tree of Thoughts prompting techniques I've found useful to start with, then stylize, then iterate

ErrorNER

Named Entity Recognition for program Error Messages

exllama-runpod-serverless

FineGrainedRLHF

h2o-wizardlm

Open-Source Implementation of WizardLM to turn documents into Q:A pairs for LLM fine-tuning

InstructZero

Official Implementation of InstructZero; the first framework to optimize bad prompts of ChatGPT(API LLMs) and finally obtain good prompts!

intercode

Code repository for InterCode benchmark

LeTI

Official repo for paper "LeTI: Learning to Generate from Textual Interactions."

llm-numbers

Numbers every LLM developer should know

novel

Notion-style WYSIWYG editor with AI-powered autocompletions

PeakProgrammer

Mastering coding precision with fine-tuned reinforcement learning

philbin

uses an LLM to generate descriptions and regular expressions for data selections

salience

automatic sentence highlights based on their significance to the document

selfcheckgpt

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

talk

Let's make sand talk

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

vec2text

utilities for decoding deep representations (like sentence embeddings) back to text