Teknium

Cofounder of Nous Research

Authored Projects (2)

Starred by

Vincent Weisser

Vincent Weisser(Cofounder of Prime Intellect) and

Jeremy Howard

Jeremy Howard(Cofounder of fast.ai).

Prompt-Engineering-Toolkit by teknium1

Web app for LLM prompt experimentation and optimization

Test prompts across multiple LLM providers (OpenAI, Anthropic).
Manage variables for dynamic prompt generation.
Save/load prompt templates and model configurations.
Compare outputs from different models side-by-side.

Created 1 year ago

Updated 1 year ago

Starred by

Jeremy Howard

Jeremy Howard(Cofounder of fast.ai),

Omar Sanseviero

Omar Sanseviero(DevRel at Google DeepMind),

Elvis Saravia

Elvis Saravia(Founder of DAIR.AI),

Jesse Clark

Jesse Clark(Cofounder of Marqo), and

1 more.

GPTeacher by teknium1

GPT-4 generated datasets for instruction tuning

General-Instruct dataset includes chain of thought, logic puzzles, and role-playing.
Roleplay-Instruct dataset focuses on tasks taking on roles of fictional characters.
Code-Instruct dataset contains ~5350 code task instructions in multiple languages.
Toolformer dataset uses predefined tools like search, Python, and Wolfram.

Created 2 years ago

Updated 2 years ago

Starred Projects (76)

firecrawl by firecrawl

API service for turning websites into LLM-ready data

tobi:

dirkenglund:

willccbb:

binarybana:

Created 1 year ago

Updated 1 day ago

atropos by NousResearch

RL environment framework for LLM trajectory collection/evaluation

hiyouga:

gakonst:

thomwolf:

pgarbacki:

Created 8 months ago

Updated 1 day ago

open-infra-index by deepseek-ai

AI infrastructure tools for efficient AGI development

lattner:

vincentweisser:

hammer:

pankajroark:

Created 10 months ago

Updated 8 months ago

reasoning-gym by open-thought

Procedural dataset generator for reasoning models

shizhediao:

ekzhu:

JustinLin610:

huybery:

Created 11 months ago

Updated 3 weeks ago

coconut by facebookresearch

Research paper implementation for LLM reasoning in latent space

winglian:

hiyouga:

alexchen4ai:

Created 1 year ago

Updated 5 months ago

antislop-sampler by sam-paech

Sampler for reducing undesirable LLM outputs via backtracking

Created 1 year ago

Updated 5 months ago

Reflection_Tuning by tianyi-lab

Research paper for LLM instruction tuning via data recycling

jph00:

winglian:

Created 2 years ago

Updated 1 year ago

Open-Reasoning-Tasks by NousResearch

Reasoning tasks collection for LLMs

zjasper666:

winglian:

JohannesHa:

philschmid:

Created 1 year ago

Updated 1 year ago

aphrodite-engine by aphrodite-engine

LLM inference engine for serving HuggingFace models at scale

luiscape:

shimmyshimmer:

vincentweisser:

jph00:

Created 2 years ago

Updated 4 days ago

Prompt-Engineering-Toolkit by teknium1

Web app for LLM prompt experimentation and optimization

vincentweisser:

jph00:

Created 1 year ago

Updated 1 year ago

dclm by mlfoundations

Framework for LLM dataset creation, training, and evaluation

hammer:

shizhediao:

CodeCreator:

Created 1 year ago

Updated 4 months ago

storm by stanford-oval

LLM system for automated knowledge curation and article generation

chiphuyen:

casper-hansen:

pgarbacki:

ogabrielluiz:

Created 1 year ago

Updated 3 months ago

ai-town by a16z-infra

AI town starter kit for building a virtual world

tobi:

bcherny:

w4nderlust:

chiphuyen:

Created 2 years ago

Updated 3 days ago

Hermes-Function-Calling by NousResearch

Function-calling code for LLMs, demoing financial queries

hiyouga:

ebursztein:

vincentweisser:

doriandarko:

Created 1 year ago

Updated 2 weeks ago

crewAI by crewAIInc

Framework for autonomous AI agent orchestration via role-playing and collaboration

tobi:

hammer:

willccbb:

smthomas:

Created 2 years ago

Updated 20 hours ago

llm_steer by Mihaiii

LLM output steering via activation engineering

Created 2 years ago

Updated 22 hours ago

mergekit by arcee-ai

CLI tool for merging pretrained language models, combining strengths without retraining

shizhediao:

Ying1123:

transitive-bullshit:

thomwolf:

Created 2 years ago

Updated 1 week ago

unified-io-2 by allenai

Unified-IO 2 code for training, inference, and demo

Jiayi-Pan:

shizhediao:

jwyang:

natolambert:

Created 2 years ago

Updated 1 year ago

dspy by stanfordnlp

Framework for programming language models, not prompting

tobi:

mateiz:

vincentweisser:

pgarbacki:

Created 3 years ago

Updated 3 days ago

distilabel by argilla-io

Framework for synthetic data and AI feedback pipelines

lvwerra:

jn2clark:

hiyouga:

pgarbacki:

Created 2 years ago

Updated 2 weeks ago

amica by semperai

Open-source interface for interactive 3D character communication

Created 2 years ago

Updated 5 months ago

galactic by taylorai

Data cleaning/curation tool for unstructured text datasets

jn2clark:

Created 2 years ago

Updated 1 year ago

data-juicer by datajuicer

Data-Juicer: Data processing system for foundation models

chiphuyen:

CodeCreator:

JustinLin610:

jph00:

Created 2 years ago

Updated 2 days ago

TinyLlama by jzhang38

Tiny pretraining project for a 1.1B Llama model

karpathy:

geohot:

tobi:

chiphuyen:

Created 2 years ago

Updated 1 year ago

gpt-llm-trainer by mshumer

LLM fine-tuning pipeline

alexanderatallah:

shyamal-anadkat:

Created 2 years ago

Updated 8 months ago

generative_agents by joonspk-research

Research paper code for interactive human behavior simulation using generative agents

tobi:

sxyu:

chiphuyen:

xiezhq-hermann:

Created 2 years ago

Updated 1 year ago

guidance by guidance-ai

Guidance is a programming paradigm for steering LLMs

tobi:

ekzhu:

stas00:

Ying1123:

Created 3 years ago

Updated 5 days ago

LLM-Blender by yuchenlin

LLM ensembling framework using pairwise ranking and generative fusion

winglian:

pgarbacki:

mlabonne:

chiphuyen:

Created 2 years ago

Updated 1 year ago

superpower-chatgpt by saeedezzati

Browser extension for enhanced ChatGPT experience

Created 2 years ago

Updated 1 year ago

talk by yacineMTB

Local conversational engine demo with audio

codekansas:

mschrage:

ggerganov:

Created 2 years ago

Updated 2 years ago

airoboros by jondurbin

Self-instruct tool for LLM finetuning

casper-hansen:

jph00:

eugeneyan:

mlabonne:

Created 2 years ago

Updated 1 year ago

llm-awq by mit-han-lab

Weight quantization research paper for LLM compression/acceleration

hiyouga:

chiphuyen:

jph00:

lysandrejik:

Created 2 years ago

Updated 5 months ago

prm800k by openai

Dataset of LLM solutions to math problems with step-level correctness labels

hiyouga:

Jiayi-Pan:

jph00:

pgarbacki:

Created 2 years ago

Updated 2 years ago

tree-of-thoughts by kyegomez

Plug-and-play implementation of Tree of Thoughts for LLM reasoning

mlabonne:

vincentweisser:

shyamal-anadkat:

omarsar:

Created 2 years ago

Updated 5 months ago

alpaca_farm by tatsu-lab

RLHF simulation framework for accessible instruction-following/alignment research

chiphuyen:

pgarbacki:

jph00:

pirroh:

Created 2 years ago

Updated 1 year ago

promptsource by bigscience-workshop

Toolkit for creating, sharing, and using natural language prompts

clmnt:

chiphuyen:

jph00:

infwinston:

Created 4 years ago

Updated 2 years ago

ReplitLM by replit

Inference code and configs for ReplitLM model family

tobi:

ishaan-jaff:

transitive-bullshit:

wsxiaoys:

Created 2 years ago

Updated 2 years ago

bittensor by opentensor

Bittensor SDK for building internet-scale neural networks

didierrlopes:

vincentweisser:

fabhed:

hammer:

Created 5 years ago

Updated 2 days ago

axolotl by axolotl-ai-cloud

CLI tool for streamlined post-training of AI models

tobi:

beyang:

zhyncs:

patrickvonplaten:

Created 2 years ago

Updated 2 days ago

UltraChat by thunlp

Multi-round dialogue dataset and models for chat language model training

jph00:

winglian:

hiyouga:

Created 2 years ago

Updated 1 year ago

OpenGPT by CogStack

Framework for grounded instruction datasets and domain-expert LLMs

winglian:

osanseviero:

Created 2 years ago

Updated 2 years ago

gpt-llama.cpp by keldenl

API wrapper for local LLM inference, emulating OpenAI's GPT endpoints

winglian:

Created 2 years ago

Updated 2 years ago

plugins-quickstart by openai

Quickstart for a ChatGPT TODO list plugin

ValentaTomas:

cbh123:

shyamal-anadkat:

logankilpatrick:

Created 2 years ago

Updated 1 year ago

threestudio by threestudio-project

Framework for 3D content generation from text/images using 2D diffusion

chiphuyen:

luiscape:

rromb:

claforte:

Created 2 years ago

Updated 1 year ago

WizardLM by nlpxucan

LLMs built using Evol-Instruct for complex instruction following

vincentweisser:

chiphuyen:

WoosukKwon:

ishaan-jaff:

Created 2 years ago

Updated 7 months ago

AIwaifu by HRNPH

Open-source project for creating a customizable AI waifu

Created 2 years ago

Updated 1 year ago

OpenCharacters by josephrocca

Web interface for chatting with customizable characters

Created 2 years ago

Updated 9 months ago

paul-graham-gpt by mckaywrigley

RAG app for Paul Graham's essays

gakonst:

mckaywrigley:

Created 2 years ago

Updated 2 years ago

SillyTavern by SillyTavern

LLM frontend for power users

chiphuyen:

doriandarko:

Created 2 years ago

Updated 16 hours ago

transformers by huggingface

ML library for pretrained model inference and training

clmnt:

lilianweng:

karpathy:

tjbck:

Created 7 years ago

Updated 1 day ago

Teenage-AGI by seanpixel

Python project for AI agent experimentation

walnutwaldo:

Created 2 years ago

Updated 2 years ago

dolly by databrickslabs

Instruction-following LLM trained on the Databricks Machine Learning Platform

mateiz:

pgarbacki:

willingc:

JustinLin610:

Created 2 years ago

Updated 2 years ago

xTuring by stochasticai

SDK for fine-tuning and customizing open-source LLMs

tobi:

chiphuyen:

borzunov:

ishaan-jaff:

Created 2 years ago

Updated 1 week ago

Bing-GPT-Voice-Assistant by Ai-Austin

Voice assistant using dual wake words

Created 2 years ago

Updated 2 years ago

DeepSpeed by deepspeedai

Deep learning optimization library for distributed training and inference

aravindsrinivas:

ValentaTomas:

winglian:

stas00:

Created 6 years ago

Updated 10 hours ago

ai-legion by eumemic

LLM-powered autonomous agent platform

mckaywrigley:

transitive-bullshit:

Created 2 years ago

Updated 7 months ago

GPT-4-LLM by Instruction-Tuning-with-GPT-4

GPT-4 data for instruction-tuning LLMs via supervised/RL

jph00:

gakonst:

marcklingen:

hammer:

Created 2 years ago

Updated 2 years ago

text-generation-inference by huggingface

Rust/Python/gRPC server for fast LLM text generation

tobi:

clmnt:

tjbck:

chiphuyen:

Created 3 years ago

Updated 3 days ago

LLaMA-Adapter by OpenGVLab

Efficient fine-tuning for instruction-following LLaMA models

jiamings:

chiphuyen:

hammer:

pgarbacki:

Created 2 years ago

Updated 1 year ago

baize-chatbot by project-baize

Chat model trained via LoRA, using ChatGPT-generated dialogs

winglian:

pgarbacki:

Ying1123:

tunguz:

Created 2 years ago

Updated 1 year ago

FastChat by lm-sys

Open platform for training, serving, and evaluating LLM-based chatbots

zjasper666:

aangelopoulos:

osanseviero:

natolambert:

Created 2 years ago

Updated 7 months ago

GPTeacher by teknium1

GPT-4 generated datasets for instruction tuning

jph00:

osanseviero:

omarsar:

jn2clark:

Created 2 years ago

Updated 2 years ago

gpt4all by nomic-ai

Desktop app for local LLM inference, no GPU/API needed

willingc:

zhiyuan8:

osanseviero:

antirez:

Created 2 years ago

Updated 7 months ago

gptq by IST-DASLab

Code for GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers

hiyouga:

chiphuyen:

gakonst:

hammer:

Created 3 years ago

Updated 1 year ago

AlpacaDataCleaned by gururise

Cleaned dataset for Alpaca LLM training

tobi:

osanseviero:

JustinLin610:

winglian:

Created 2 years ago

Updated 2 years ago

point-alpaca by pointnetwork

Fine-tuned LLaMA weights, recreated from Stanford Alpaca

Created 2 years ago

Updated 2 years ago

GPTQ-for-LLaMa by qwopqwop200

4-bit quantization for LLaMA models using GPTQ

chiphuyen:

gakonst:

hiyouga:

soldni:

Created 2 years ago

Updated 1 year ago

wolverine by biobootloader

Tool for regenerative healing of Python scripts using GPT

danielgross:

paul-gauthier:

nirga:

marcklingen:

Created 2 years ago

Updated 1 year ago

FasterTransformer by NVIDIA

Optimized transformer library for inference

nat:

chiphuyen:

JustinLin610:

mfuntowicz:

Created 4 years ago

Updated 1 year ago

Kuebiko by adi-panda

AI Twitch chat bot using GPT-3 and Google Cloud TTS

Created 3 years ago

Updated 1 year ago

stanford_alpaca by tatsu-lab

Instruction-following LLaMA model training and data generation

karpathy:

john-b-yang:

pgarbacki:

osanseviero:

Created 2 years ago

Updated 1 year ago

llm by rustformers

Rust ecosystem for LLM Rust inference (unmaintained)

chiphuyen:

luiscape:

swyxio:

flaque:

Created 2 years ago

Updated 1 year ago

ChatWaifu by cjyaddone

Chatbot for simulating conversations with waifu-style characters

Created 3 years ago

Updated 1 year ago

alpaca-lora by tloen

LoRA fine-tuning for LLaMA

JustinLin610:

vincentweisser:

nirga:

chiphuyen:

Created 2 years ago

Updated 1 year ago

OpenChatKit by togethercomputer

Open-source toolkit for building specialized/general-purpose chat models

AntonOsika:

pgarbacki:

winglian:

casper-hansen:

Created 2 years ago

Updated 1 year ago

minimal-llama by zphang

Code for running and fine-tuning LLaMA models

pgarbacki:

winglian:

jamesr66a:

Created 2 years ago

Updated 2 years ago

Feedback? Help us improve.