hmzo's starred repositories
chatgpt_system_prompt
A collection of GPT system prompts and various prompt injection/leaking knowledge.
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
alignment-handbook
Robust recipes to align language models with human and AI preferences
hyperlearn
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
persona-hub
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
RLHF-Reward-Modeling
Recipes to train reward model for RLHF.
attention_sinks
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
LLM-Shearing
[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
gpt_paper_assistant
GPT4 based personalized ArXiv paper assistant bot
Online-RLHF
A recipe for online RLHF and online iterative DPO.
NeuralFlow
Visualize the intermediate output of Mistral 7B