Open Source Python Large Language Models (LLM) - Page 13
Sort By:
Python Large Language Models (LLM)
View 367 business solutionsBrowse free open source Python Large Language Models (LLM) and projects below. Use the toggles on the left to filter open source Python Large Language Models (LLM) by OS, license, language, programming language, and project status.
-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
LightLLM
LightLLM is a Python-based LLM (Large Language Model) inference
LightLLM is a high-performance inference and serving framework designed specifically for large language models, focusing on lightweight architecture, scalability, and efficient deployment. The framework enables developers to run and serve modern language models with significantly improved speed and resource efficiency compared to many traditional inference systems. Built primarily in Python, the project integrates optimization techniques and ideas from several leading open-source implementations, including FasterTransformer, vLLM, and FlashAttention, to accelerate token generation and reduce latency. LightLLM is designed to handle large-scale model workloads in production environments, supporting efficient batching and GPU utilization for fast inference across multiple requests. Its architecture allows models to be deployed with minimal overhead while maintaining compatibility with popular transformer-based model families such as LLaMA and GPT-style architectures. -
2
Ling
Ling is a MoE LLM provided and open-sourced by InclusionAI
Ling is a Mixture-of-Experts (MoE) large language model (LLM) provided and open-sourced by inclusionAI. The project offers different sizes (Ling-lite, Ling-plus) and emphasizes flexibility and efficiency: being able to scale, adapt expert activation, and perform across a range of natural language/reasoning tasks. Example scripts, inference pipelines, and documentation. The codebase includes inference, examples, models, documentation, and model download infrastructure. As more developers and researchers engage with the platform, we can expect rapid advancements and improvements, leading to even more sophisticated applications. Model inference and API code (e.g. integration with Transformers). This collaborative approach accelerates development and ensures that the models remain at the forefront of technology, addressing emerging challenges in various fields. -
3
Llama-Chinese
Llama Chinese community, real-time aggregation
Llama-Chinese is an open source community initiative focused on adapting and improving Meta’s LLaMA language models for Chinese language applications. The project aggregates datasets, research resources, tutorials, and tools that help developers train and fine-tune LLaMA-based models with Chinese linguistic capabilities. It also provides optimized versions of LLaMA models trained on large-scale Chinese datasets to improve performance in tasks such as translation, summarization, and conversational AI. The community maintains educational materials and technical documentation that help researchers understand the process of training and deploying Chinese-optimized large language models. In addition to model development, the project collects learning resources and open research contributions related to LLM technology in Chinese environments. Overall, Llama-Chinese acts as both a technical ecosystem and knowledge hub dedicated to advancing Chinese-language large model development. -
4
LlamaGen
Autoregressive Model Beats Diffusion
LlamaGen is an open-source research project that introduces a new approach to image generation by applying the autoregressive next-token prediction paradigm used in large language models to visual generation tasks. Instead of relying on diffusion models, the framework treats images as sequences of tokens that can be generated progressively using transformer architectures similar to those used for text generation. The project explores how scaling autoregressive models and improving image tokenization techniques can produce competitive results compared with modern diffusion-based image generators. LlamaGen provides several pre-trained models and training configurations that support both class-conditional image generation and text-conditioned image synthesis. The repository includes image tokenizers, training scripts, and models ranging from hundreds of millions to several billion parameters. -
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
5
Local File Organizer
An AI-powered file management tool that ensures privacy
Local-File-Organizer is an AI-powered file management system designed to automatically analyze, categorize, and reorganize files stored on a user’s local machine. The project focuses on privacy-first file organization by performing all processing locally rather than sending data to external cloud services. It uses language and vision models to understand the contents of documents, images, and other file types so that files can be grouped intelligently according to their meaning or context. The system scans directories, extracts relevant information from files, and restructures folder hierarchies to make content easier to locate and manage. Through AI-driven analysis, the software can detect themes, topics, and metadata in files, allowing it to organize information in ways that traditional rule-based file managers cannot achieve. The tool supports multiple sorting strategies that allow users to categorize files by content, date, or type depending on their workflow preferences. -
6
LongBench
LongBench v2 and LongBench (ACL 25'&24')
LongBench is a comprehensive benchmark designed to evaluate the ability of large language models to understand and reason over very long textual contexts. Traditional language model benchmarks typically evaluate tasks involving relatively short inputs, which does not reflect many real-world applications such as analyzing large documents or entire code repositories. LongBench addresses this gap by providing datasets that require models to process and reason over long sequences of text across multiple tasks. The benchmark includes multiple categories such as single-document question answering, multi-document reasoning, summarization, long dialogue understanding, and code analysis. It supports bilingual evaluation in English and Chinese to assess multilingual capabilities across extended contexts. Newer versions of the benchmark introduce extremely long context windows ranging from thousands to millions of tokens, enabling researchers to test the limits of modern long-context models. -
7
LongWriter
Unleashing 10,000+ Word Generation from Long Context LLMs
LongWriter is an open-source framework and set of large language models designed to enable ultra-long text generation that can exceed 10,000 words while maintaining coherence and structure. Traditional large language models can process large inputs but often struggle to generate long outputs due to limitations in training data and alignment strategies. LongWriter addresses this challenge by introducing a specialized dataset and training approach that encourages models to produce longer responses. The system uses an agent-based pipeline called AgentWrite that decomposes large writing tasks into smaller subtasks, allowing the model to produce long documents section by section. Researchers also created the LongWriter-6k dataset containing thousands of examples with outputs ranging from a few thousand to tens of thousands of words. -
8
MGIE
Guiding Instruction-based Image Editing via Multimodal Large Language
MGIE—Guiding Instruction-based Image Editing—demonstrates how a multimodal LLM can parse natural-language editing instructions and then drive image transformations accordingly. The project focuses on making edits explainable and controllable: the model interprets text guidance, reasons over image content, and outputs edits aligned with user intent. It’s positioned as an ICLR 2024 Spotlight work, with code and references that show how to connect language planning to concrete image operations. This bridges a gap between free-form prompts and precise edits by letting users describe “what” and “where” in everyday language. The repo includes instructions, examples, and links that situate MGIE within Apple’s broader line of multimodal research. For practitioners, MGIE provides a blueprint for text-to-edit systems that are more semantically grounded than naive prompt-only pipelines. -
9
MING
A large-scale model of medical consultation in Chinese
MING is an open-source medical large language model designed for intelligent medical consultation and question answering in Chinese. The project focuses on building a healthcare-focused conversational system capable of responding to medical questions, analyzing case descriptions, and guiding diagnostic reasoning. It is trained using medical instruction tuning so that the model can understand patient symptoms and respond with structured explanations and clinical suggestions. One of its primary goals is to simulate a multi-round medical consultation process, allowing the system to ask follow-up questions before offering diagnostic recommendations. This interactive capability makes it suitable for conversational health applications, patient triage scenarios, and educational demonstrations. The model is built on transformer-based architectures using frameworks such as PyTorch and integrates with Hugging Face tooling for training and inference workflows. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
ML Ferret
Refer and Ground Anything Anywhere at Any Granularity
Ferret is Apple’s end-to-end multimodal large language model designed specifically for flexible referring and grounding: it can understand references of any granularity (boxes, points, free-form regions) and then ground open-vocabulary descriptions back onto the image. The core idea is a hybrid region representation that mixes discrete coordinates with continuous visual features, so the model can fluidly handle “any-form” referring while maintaining precise spatial localization. The repo presents the vision-language pipeline, model assets, and paper resources that show how Ferret answers questions, follows instructions, and returns grounded outputs rather than just text. In practice, this enables tasks like “find that small red icon next to the chart and describe it” where both the linguistic reference and the visual region are ambiguous without fine spatial reasoning. -
11
ML Retreat
Machine Learning Journal for Intermediate to Advanced Topics
ML Retreat is an open-source learning repository that serves as a structured journal documenting advanced topics in machine learning and artificial intelligence. The project compiles detailed notes, technical explanations, and curated resources that guide readers through complex concepts across modern AI research. Rather than functioning as a traditional tutorial series, the repository is organized as a learning journey that progressively explores increasingly advanced subjects. Topics include large language models, graph neural networks, mechanistic interpretability, transformer architectures, and emerging research areas such as quantum machine learning. The repository includes references to influential research papers, lectures, and educational content from well-known machine learning educators. -
12
Magicoder
Empowering Code Generation with OSS-Instruct
Magicoder is an open-source family of large language models designed specifically for code generation and software development tasks. The project focuses on improving the quality and diversity of code generation by training models with a novel dataset construction approach known as OSS-Instruct. This technique uses open-source code repositories as a foundation for generating more realistic and diverse instruction datasets for training language models. By grounding training data in real open-source examples, Magicoder aims to reduce bias and improve the reliability of code generation results compared to models trained solely on synthetic instructions. The project includes model implementations, training resources, and evaluation benchmarks that demonstrate how the approach improves instruction-following and code synthesis capabilities. Magicoder models are intended for tasks such as programming assistance, code explanation, automated debugging, and software documentation generation. -
13
MatMul-Free LM
Implementation for MatMul-free LM
MatMul-Free LM is an experimental implementation of a large language model architecture designed to eliminate traditional matrix multiplication operations used in transformer networks. Since matrix multiplication is one of the most computationally expensive components of modern language models, the project explores alternative computational strategies that reduce hardware requirements while maintaining comparable performance. The architecture relies on quantization-aware training and lightweight operations to replace conventional dense matrix multiplications with more efficient alternatives. These optimizations can significantly reduce memory consumption and potentially improve computational efficiency during both training and inference. The repository provides implementations of models at several parameter scales and includes tools for experimenting with the architecture using modern machine learning frameworks. -
14
MaxText
A simple, performant and scalable Jax LLM
MaxText is a high-performance, highly scalable open-source framework designed to train and fine-tune large language models using the JAX ecosystem. The project acts as both a reference implementation and a practical training library that demonstrates best practices for building and scaling transformer-based language models on modern accelerator hardware. It is optimized to run efficiently on Google Cloud TPUs and GPUs, enabling researchers and engineers to train models ranging from small experiments to extremely large distributed workloads. The framework focuses on simplicity while still supporting advanced techniques such as model sharding, distributed computation, and high-throughput training pipelines. MaxText includes ready-to-use configurations and reproducible training examples that help developers understand how to deploy large-scale AI workloads with modern machine learning infrastructure. -
15
MegaParse
File Parser optimised for LLM Ingestion with no loss
MegaParse is a file parser optimized for Large Language Model (LLM) ingestion, ensuring no loss of information. It efficiently parses various document formats, such as PDFs, DOCX, and PPTX, converting them into formats ideal for processing by LLMs. This tool is essential for applications that require accurate and comprehensive data extraction from diverse document types. -
16
Megatron
Ongoing research training transformer models at scale
Megatron is a large, powerful transformer developed by the Applied Deep Learning Research team at NVIDIA. This repository is for ongoing research on training large transformer language models at scale. We developed efficient, model-parallel (tensor, sequence, and pipeline), and multi-node pre-training of transformer based models such as GPT, BERT, and T5 using mixed precision. Megatron is also used in NeMo Megatron, a framework to help enterprises overcome the challenges of building and training sophisticated natural language processing models with billions and trillions of parameters. Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved. -
17
MemoryOS
MemoryOS is designed to provide a memory operating system
MemoryOS is an open-source framework designed to provide a structured memory management system for AI agents and large language model applications. The project addresses one of the major limitations of modern language models: their inability to maintain long-term context beyond the limits of their prompt window. MemoryOS introduces a hierarchical memory architecture inspired by operating system memory management principles, allowing agents to store, update, retrieve, and generate information from multiple layers of memory. These layers typically include short-term memory for immediate conversation context, mid-term memory for topic-level grouping, and long-term personal memory for persistent knowledge about users or tasks. The system dynamically updates and promotes information between these layers using structured algorithms that prioritize relevance and recency. -
18
MiniMax-01
Large-language-model & vision-language-model based on Linear Attention
MiniMax-01 is the official repository for two flagship models: MiniMax-Text-01, a long-context language model, and MiniMax-VL-01, a vision-language model built on top of it. MiniMax-Text-01 uses a hybrid attention architecture that blends Lightning Attention, standard softmax attention, and Mixture-of-Experts (MoE) routing to achieve both high throughput and long-context reasoning. It has 456 billion total parameters with 45.9 billion activated per token and is trained with advanced parallel strategies such as LASP+, varlen ring attention, and Expert Tensor Parallelism, enabling a training context of 1 million tokens and up to 4 million tokens at inference. MiniMax-VL-01 extends this core by adding a 303M-parameter Vision Transformer and a two-layer MLP projector in a ViT–MLP–LLM framework, allowing the model to process images at dynamic resolutions up to 2016×2016. -
19
MiniMax-M1
Open-weight, large-scale hybrid-attention reasoning model
MiniMax-M1 is presented as the world’s first open-weight, large-scale hybrid-attention reasoning model, designed to push the frontier of long-context, tool-using, and deeply “thinking” language models. It is built on the MiniMax-Text-01 foundation and keeps the same massive parameter budget, but reworks the attention and training setup for better reasoning and test-time compute scaling. Architecturally, it combines Mixture-of-Experts layers with lightning attention, enabling the model to support a native context length of 1 million tokens while using far fewer FLOPs than comparable reasoning models for very long generations. The team emphasizes efficient scaling of test-time compute: at 100K-token generation lengths, M1 reportedly uses only about 25 percent of the FLOPs of some competing models, making extended “think step” traces more feasible. M1 is further trained with large-scale reinforcement learning over diverse tasks. -
20
MiniOneRec
Minimal reproduction of OneRec
MiniOneRec is an open-source framework designed to explore generative approaches to recommendation systems using large language model architectures. Traditional recommender systems typically rely on large embedding tables and ranking models, but MiniOneRec adopts a generative paradigm in which items are represented as sequences of semantic identifiers generated by autoregressive models. The framework provides an end-to-end pipeline for building generative recommender systems, including semantic identifier construction, supervised fine-tuning, and reinforcement learning-based optimization. Semantic IDs are created using techniques such as quantized variational autoencoders to convert item features into token sequences that can be modeled by transformer architectures. Developers can train and evaluate recommendation models using different backbone language models while benefiting from the generative framework’s parameter efficiency and scalability. -
21
Mixtral offloading
Run Mixtral-8x7B models in Colab or consumer desktops
Mixtral-Offloading is an open-source project designed to enable efficient inference of large Mixture-of-Experts language models such as Mixtral-8x7B on hardware with limited GPU memory. The project implements techniques that allow model components to be dynamically moved between CPU memory and GPU memory during inference, significantly reducing the amount of GPU VRAM required to run the model. This approach takes advantage of the sparse activation properties of mixture-of-experts architectures, where only a subset of expert networks are used for each token during generation. By selectively loading and caching the required experts, the system avoids keeping the entire model in GPU memory at once. The repository includes notebooks and code examples that demonstrate how to run large language models on consumer hardware such as personal GPUs or cloud notebook environments. -
22
MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
MoBA, short for Mixture of Block Attention, is an open-source research implementation of a novel attention mechanism designed to improve the efficiency of large language models processing extremely long contexts. The architecture adapts ideas from Mixture-of-Experts networks and applies them directly to the attention mechanism of transformer models. Instead of forcing each token to attend to every other token in the sequence, MoBA divides the context into blocks and dynamically routes queries to only the most relevant segments of information. This routing strategy reduces the computational cost associated with traditional attention while preserving performance on reasoning and long-context tasks. The approach allows language models to scale to significantly longer input contexts without the quadratic computational cost normally associated with transformer attention mechanisms. -
23
NExT-GPT
Code and models for ICML 2024 paper, NExT-GPT
NExT-GPT is an open-source research framework that implements an advanced multimodal large language model capable of understanding and generating content across multiple modalities. Unlike traditional models that primarily handle text, NExT-GPT supports input and output combinations involving text, images, video, and audio in a unified architecture. The system connects a large language model with multimodal encoders and diffusion-based decoders so it can interpret information from different sensory formats and generate responses in different media types. This architecture allows the model to convert between modalities, such as generating images from text descriptions or producing audio or video outputs based on textual prompts. The project also introduces instruction-tuning strategies that enable the model to perform complex multimodal reasoning and generation tasks with minimal additional parameters. -
24
NeMo Curator
Scalable data pre processing and curation toolkit for LLMs
NeMo Curator is a Python library specifically designed for fast and scalable dataset preparation and curation for large language model (LLM) use-cases such as foundation model pretraining, domain-adaptive pretraining (DAPT), supervised fine-tuning (SFT) and paramter-efficient fine-tuning (PEFT). It greatly accelerates data curation by leveraging GPUs with Dask and RAPIDS, resulting in significant time savings. The library provides a customizable and modular interface, simplifying pipeline expansion and accelerating model convergence through the preparation of high-quality tokens. At the core of the NeMo Curator is the DocumentDataset which serves as the the main dataset class. It acts as a straightforward wrapper around a Dask DataFrame. The Python library offers easy-to-use methods for expanding the functionality of your curation pipeline while eliminating scalability concerns. -
25
NewsNotFound
This is the entire source code for NewsNotFound's article gen process
Our mission is to lead the way in AI journalism by providing completely neutral and unbiased news articles that can be governed by the public. NewsNotFound is a news website located at https://newsnotfound.com. We want to build the most unbiased news platform on the internet.
