darquedante Goto Github PK

aistuff

Lez AI dat betch

chatlm-smol-0.2b

Smol Conversation 0.2 Billion Smol Model (ChatLM-Smol-0.2B), open-sourced all code for data collection, data cleaning, tokenizer training, model pretraining, SFT instruction fine-tuning, RLHF optimization, and other processes. Supports downstream tasks SFT fine-tuning and provides an example of triplet information extraction fine-tuning.

darquedante.github.io

Smol site about small LLM's and other projects

generative-ai-for-beginners

12 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

gpt-sovits-en

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

help_desk_crm

SITS Help Desk CRM Project in Access 2010

llm_course_notebooks

llmsfromscratchbuilder

Attention is all you need implementation

macrogpt-pretrain

macrogpt大模型全量预训练(1b3,32层), 多卡deepspeed/单卡adafactor

microgpt_v2

Implementation of GPT from scratch. Design to be lightweight and easy to modify.

mygpt-testing

An easily-trained baby GPT that can stand in for the real thing. Based on Andrej Karpathy's makemore, but set up to mimic a llama-cpp server. This is not production-ready; it's a toy implementation for educational purposes.

phi2-smol-0.2b

# Phi2-Smol-0.2B: Train your own small Phi2 English model from scratch, with support for integrating with langchain to load a local knowledge base for enhanced retrieval generation RAG. # Training your own Phi2 small chat model from scratch.

picogpt

pokemonpythonnumberascii

pretrain_bart

training BART from scratch

pretraining-data-packing

privategpt

Interact privately with your documents using the power of GPT, 100% privately, no data leaks - Modified for Google Colab /Cloud Notebooks

retrieval-based-voice-conversion-webui-en

Voice data <= 10 mins can also be used to train a good VC model!

rw.rs

free shell account and web 1.0 hosting @ http://rw.rs/~you

scratch2lm

Training transformer models (e.g. RoBERTa, GPT2 and GPT-J) from scratch.

simple-bert-roberta-pretrain

You just need ONE script for the whole pretraining process! HuggingFace reproduction of the BERT/RoBERTa pretraining from scratch, with memory optimization using DeepSpeed and BF16.

simplegpt

Smol implementation of a GPT (training and inference) in PyTorch.

simplegptfromscratch

A codebase implementing a simple GPT-like model from scratch based on the Attention is All You Need paper.

so-vits-svc-5.0-en

Core Engine of Singing Voice Conversion & Singing Voice Clone

sophia

The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”

suck-o-rama

Python 3 / Tkinter gopher client with unicode support.

tinyllama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

transformer-neural-network

Code Transformer neural network components piece by piece

unnamedcligopherbrowser

An Un-named CLI gopher browser written in python3

zserge-webview

Tiny cross-platform webview library for C/C++/Golang. Uses WebKit (Gtk/Cocoa) and Edge (Windows)