cg123

dspy

DSPy: The framework for programming—not prompting—foundation models

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

mamba

Mamba SSM architecture

mergekit

Tools for merging pretrained large language models.

sd-forge-layerdiffuse

[WIP] Layer Diffusion for WebUI (via Forge)

smoltcp

a smol tcp/ip stack

functionary

Chat language model that can use tools and interpret the results

distilabel

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

JetMoE

Reaching LLaMA2 Performance with 0.1M Dollars

godot_rl_agents

An Open Source package that allows video game creators, AI researchers and hobbyists the opportunity to learn complex behaviors for their Non Player Characters or agents

symbolica

A modern computer algebra system which aims to handle expressions with billions of terms.

pareas

GPU-accelerated compiler

PolyMind

A multimodal, function calling powered LLM webui.

tensorizer

Module, Model, and Tensor Serialization/Deserialization

scattermoe

Triton-based implementation of Sparse Mixture of Experts.

BitMat

An efficent implementation of the method proposed in "The Era of 1-bit LLMs"

PruneMe

Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models

zett

Code for Zero-Shot Tokenizer Transfer

tiny-asic-1_58bit-matrix-mul

Tiny ASIC implementation for "The Era of 1-bit LLMs All Large Language Models are in 1.58 Bits" matrix multiplication unit

MergeMonster

An unsupervised model merging algorithm for Transformers-based language models.

tangent_task_arithmetic

Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".

TerDiT

TerDiT: Ternary Diffusion Models with Transformers

Gymbo

gradient-based symbolic execution engine implemented from scratch

tinynarrations

A synthetic story narration dataset to study small audio LMs.

zaraki-tools

mergeui

All-in-one UI for merged LLMs in Hugging Face

training_free_model_merging

This repository is the implementation of the paper Training Free Pretrained Model Merging (CVPR2024).

merging-text-transformers

Code for "Merging Text Transformers from Different Initializations"

Task-Vector-Merge-Optimzier

YuisekinAI-mergekit