gauss5930

AlpaGasus2-QLoRA

This is AlpaGasus2-QLoRA based on LLaMA2 with AlpaGasus mechanism using QLoRA!

arena-hard-auto

Arena-Hard-Auto: An automatic LLM benchmark.

Deep-Learning-Paper

These are papers that I read and reviewed related to NLP, CV, and Deep Learning 😉 You can check paper links and my reviews 😊

gauss5930

gauss5930.github.io

Hermes

Huggingface-Course

iDUS

An unofficial implementation of SOLAR-10.7B model and the newly proposed interlocked-DUS(iDUS) implementation and experiment details.

KoRAE

LLM-Agora

LLM Agora, debating between open-source LLMs to refine the answers

gauss5930/LLM-Agora

LLM Agora, debating between open-source LLMs to refine the answers

gauss5930/AlpaGasus2-QLoRA

This is AlpaGasus2-QLoRA based on LLaMA2 with AlpaGasus mechanism using QLoRA!

gauss5930/Deep-Learning-Paper

These are papers that I read and reviewed related to NLP, CV, and Deep Learning 😉 You can check paper links and my reviews 😊

gauss5930/iDUS

An unofficial implementation of SOLAR-10.7B model and the newly proposed interlocked-DUS(iDUS) implementation and experiment details.

gauss5930/KoRAE

gauss5930/FastChat

This is copy of repo for Vicuna and Chatbot Arena.

gauss5930/gauss5930

gauss5930/gauss5930.github.io

gauss5930/Hermes

gauss5930/Huggingface-Course

gauss5930/OCIP

gauss5930/k2-eval

gauss5930/LLMTest_NeedleInAHaystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

gauss5930/Megatron-LM-NEO

gauss5930/Quantization

The comparison of most popular quantization methods, BitsAndBytes and GPTQ

gauss5930/transformer-implementation

The PyTorch implementation of Transformer

gauss5930/URIAL