sensitiveanalyst

textgrad

Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

Qwen2

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

LLM-Merging

LLM-Merging: Building LLMs Efficiently through Merging

devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

MACM

MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems

AutoCoder

We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.

SimPO

SimPO: Simple Preference Optimization with a Reference-Free Reward

ObsScaling

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

Devon

Devon: An open-source pair programmer

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

kanrl

Kolmogorov-Arnold Network for Reinforcement Leaning, initial experiments

Kolmogorov-Arnold-Networks-KANs-mlx

Composio-Function-Calling-Benchmark

Function Calling Benchmark & Testing

KAN

Implementation on how to use Kolmogorov-Arnold Networks (KANs) for classification and regression tasks.

Deep-KAN

This repository contains a better implementation of Kolmogorov-Arnold networks

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

pykan

Kolmogorov Arnold Networks

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

vllm

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

penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

simple-federated-learning

merge-models

Merges two latent diffusion models at a user-defined ratio

mergekit

Tools for merging pretrained large language models.

evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.