zhutony

agent_tutorials

various agent tutorials

ai-workshop-code

Code I wrote for my AI & LLM workshops

astro

The web framework for content-driven websites. ⭐️ Star to support our work!

AutoCoder

We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.

cognita

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

corenet

CoreNet: A library for training deep neural networks

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

docs

documentation for content creation

elia

A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

GrokkedTransformer

Code for the paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'

iceberg

Apache Iceberg

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

llama-fs

A self-organizing file system with llama 3

marker

Convert PDF to markdown quickly with high accuracy

MiniCPM

MiniCPM-2B: An end-side LLM outperforms Llama2-13B.

my-notes

nanotron

Minimalistic large language model 3D-parallelism training

PATE

Official repository for “PATE: Proximity-Aware Time series anomaly Evaluation”.

pykan

Kolmogorov Arnold Networks

pyreft

ReFT: Representation Finetuning for Language Models

pytorch_fun

pyvene

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

Scrapegraph-ai

Python scraper based on AI

Time-LLM

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

Time-Series-Library

A Library for Advanced Deep Time Series Models.

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.