vertinski's Projects
Instruct-tune LLaMA on consumer hardware
Alpaca dataset from Stanford, cleaned and curated
An experimental open-source attempt to make GPT-4 fully autonomous.
š Text-Prompted Generative Audio Model
A repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.
Use commands in English to control Blender with OpenAI's GPT-4
API for interacting with ChatGPT using Python and from Shell.
The Cobra programming language
This code is produced using OpenAI Codex model
This program automatically runs Python code copied in clipboard
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
DOOM-style 3D (raycasting) Game in Python Pygame
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Motion tracking avatar
A fast inference library for running LLMs locally on modern consumer-class GPUs
GLM-130B: An Open Bilingual Pre-Trained Model
gzip based LLM
Converts text input or URL into knowledge graph and displays
The community of Alpaca developers and users
ā” Building applications with LLMs through composability ā”
just checking if code works properly
Improved GPT-3.5 Agent (with tools) for GPT-3.5
LIGMAScript (the bestest programming language ever) compiler and interpreter
Inference Llama 2 in one file of pure C
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Drive a browser with GPT-3
š¤ PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Audio compression/decompression tools for internet