Teknium

GPTeacher. A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer

Prompt-Engineering-Toolkit. JavaScript

alpaca-roleplay-discordbot. A discord bot that roleplays!

LLM-Benchmark-Logs. Just a bunch of benchmark logs for different LLMs

ShareGPT-Builder. Python

alpaca-discord. A Simple Discord Bot for the Alpaca LLM

character-cards. A collection of character cards for use in AI Roleplaying

hermes-miniverse. Bridge connecting Hermes Agent to Miniverse pixel worlds

stanford_alpaca-replit. Modified Stanford-Alpaca Trainer for Training Replit's Code Model

transformers-gptq-quant. Python

LLM-Logbook. Public reports detailing responses to sets of prompts by Large Language Models.

RawTransform. A repository of prompts and Python scripts for intelligent transformation of raw text into diverse formats.

nous-discord-archive. Auto-archived text logs of Nous Research Discord channels (polled every 6h)

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

teknium1. Config files for my GitHub profile.

ez-pokedex. gemini 2.5 made it

atropos. Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments

Open-Reasoning-Tasks. A comprehensive repository of reasoning tasks for LLMs (and beyond)

font-editor. JavaScript

gpt-llm-trainer. Jupyter Notebook

AlpacaDataCleaned. Alpaca dataset from Stanford, cleaned and curated

hermetic-codex-docs. Documentation site for The Hermetic Codex — a Minecraft 1.21.1 NeoForge modpack.

hermetic-codex-tweaks. Companion client mod for The Hermetic Codex modpack — configurable Cobblemon party HUD position.

NemoClaw. Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

teknium1.github.io. HTML

gpt4all.io. JavaScript

MixEval. The official evaluation suite and dynamic data release for MixEval.

cosmopedia. Python

logit-bias-pool. Python

axolotl. Go ahead and axolotl questions

lm-evaluation-harness. A framework for few-shot evaluation of autoregressive language models.

treasure_trove. Jupyter Notebook

finetune-study. Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.

functionary. Chat language model that can interpret and execute functions/plugins

chai-guanaco. Official pip package for the Chai Guanaco Competition

codealpaca. Python

alpagasus. Unofficial implementation of AlpaGasus

arena-hard-auto. Arena-Hard-Auto: An automatic LLM benchmark.