My answers to Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2022)

QLoRA with Enhanced Multi GPU Support

GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ

QLoRA: Efficient Finetuning of Quantized LLMs

Llama 2 Everywhere (L2E)

QLoRA: Efficient Finetuning of Quantized LLMs

Homoglyphs: get similar letters, convert to ASCII, detect possible languages and UTF-8 group.

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

A curated list of awesome Java frameworks, libraries and software.

Java annotation-based framework for parsing Git like command line structures with deep extensibility