☄️ Highly customisable markdown(latex & inline html) previewer for Neovim

This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.

Ellama is a tool for interacting with large language models from Emacs.

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

LLM training in simple, raw C/CUDA

A readline wrapper

LOMO: LOw-Memory Optimization

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

北京航空航天大学计算机学院开题报告/文献综述

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Emacs Configuration init files

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

Code for "Democratizing Reasoning Ability: Tailored Learning from Large Language Model", EMNLP 2023

Splatoon 2 Octo Expansion CQ-80 terminal replica

Code for Paper: “Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

A terminal written in PyQt6 for the Emacs Application Framework.

An interface to communicate with Jupyter kernels.

Rime 配置：雾凇拼音 | 长期维护的简体词库

✨ Magical shell history

Make GitHub Copilot CLI's alias work for Fish shell

PECOS - Prediction for Enormous and Correlated Spaces

Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph

My emacs configurations

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".