leegao

llama.cpp

LLM inference in C/C++

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

txtai

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

chat-ui

Open source codebase powering the HuggingChat app

llmware

Unified framework for building enterprise RAG pipelines with small, specialized models

Anima

33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

rift

Rift: an AI-native language server for your personal AI software engineer

mergekit

Tools for merging pretrained large language models.

notebooks

EasyEdit

An Easy-to-use Knowledge Editing Framework for LLMs.

FastEdit

🩹Editing large language models within 10 seconds⚡

yarn

YaRN: Efficient Context Window Extension of Large Language Models

attention_sinks

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

KnowledgeEditingPapers

Must-read Papers on Knowledge Editing for Large Language Models.

augmentoolkit

Convert Compute And Books Into Instruct-Tuning Datasets

laser

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

ai-clone-whatsapp

Create an AI clone of yourself from your WhatsApp chats (using Llama 3)

laserRMT

This is our own implementation of 'Layer Selective Rank Reduction'

LLaMa2lang

Convenience scripts to finetune (chat-)LLaMa3 and other models for any language

large-sequence-modeling

Transformers with Arbitrarily Large Context, No Approximations

LLM-Alchemy-Chamber

a friendly neighborhood repository with diverse experiments and adventures in the world of LLMs

selfextend

an implementation of Self-Extend, to expand the context window via grouped attention

gbnfgen

TypeScript generator for llama.cpp Grammar directly from TypeScript interfaces

langfun

Empower LLMs with Symbols.

Entropy-ABF

Official implementation for 'Extending LLMs’ Context Window with 100 Samples'

BrainHackingChip

Brain-Hacking Chip: inject negative prompts directly into your LLM's thoughts with this oobabooga extension!

SelfExtend

Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta

laserRMT-encoder

Fork of Fernandos implementation of 'Layer Selective Rank Reduction'