Open Source Python Large Language Models (LLM) - Page 3
Sort By:
Python Large Language Models (LLM)
View 375 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.
-
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
1
self-llm
Tutorial tailored for Chinese babies on rapid fine-tuning
self-llm is an open source educational project created by the Datawhale community that serves as a practical guide for deploying, fine-tuning, and using open-source large language models on Linux systems. The repository focuses on helping beginners and developers understand how to run and customize modern LLMs locally rather than relying solely on hosted APIs. It provides step-by-step tutorials covering environment setup, model deployment, inference workflows, and efficient fine-tuning techniques such as LoRA and parameter-efficient training. The project also includes guides for integrating models into real applications, including command-line interfaces, web demos, and frameworks like LangChain. By combining theory, configuration instructions, and runnable examples, self-llm lowers the barrier to entry for students and engineers who want to experiment with open-source models. -
2
Agentic Context Engine
Make your agents learn from experience
Agentic Context Engine (ACE) is an open-source framework designed to help AI agents improve their performance by learning from their own execution history. Instead of relying solely on model training or fine-tuning, the framework focuses on structured context engineering, allowing agents to accumulate knowledge from past successes and failures during task execution. The system treats context as a dynamic “playbook” that evolves over time through a process of generation, reflection, and curation, enabling agents to refine strategies across repeated tasks. In this workflow, one component generates solutions, another reflects on outcomes, and a third curates useful knowledge so it can be reused in future interactions. This architecture allows agents to gradually build persistent operational memory without requiring additional training datasets or model retraining. -
3
CogVLM2
GPT4V-level open-source multi-modal model based on Llama3-8B
CogVLM2 is the second generation of the CogVLM vision-language model series, developed by ZhipuAI and released in 2024. Built on Meta-Llama-3-8B-Instruct, CogVLM2 significantly improves over its predecessor by providing stronger performance across multimodal benchmarks such as TextVQA, DocVQA, and ChartQA, while introducing extended context length support of up to 8K tokens and high-resolution image input up to 1344×1344. The series includes models for both image understanding and video understanding, with CogVLM2-Video supporting up to 1-minute videos by analyzing keyframes. It supports bilingual interaction (Chinese and English) and has open-source versions optimized for dialogue and video comprehension. Notably, the Int4 quantized version allows efficient inference on GPUs with only 16GB of memory. The repository offers demos, API servers, fine-tuning examples, and integration with OpenAI API-compatible endpoints, making it accessible for both researchers and developers. -
4
GPT Neo
An implementation of model parallel GPT-2 and GPT-3-style models
An implementation of model & data parallel GPT3-like models using the mesh-tensorflow library. If you're just here to play with our pre-trained models, we strongly recommend you try out the HuggingFace Transformer integration. Training and inference is officially supported on TPU and should work on GPU as well. This repository will be (mostly) archived as we move focus to our GPU-specific repo, GPT-NeoX. NB, while neo can technically run a training step at 200B+ parameters, it is very inefficient at those scales. This, as well as the fact that many GPUs became available to us, among other things, prompted us to move development over to GPT-NeoX. All evaluations were done using our evaluation harness. Some results for GPT-2 and GPT-3 are inconsistent with the values reported in the respective papers. We are currently looking into why, and would greatly appreciate feedback and further testing of our eval harness. -
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.
-
5
GPT-API-free
Free ChatGPT&DeepSeek API Key
GPT-API-free is a project that provides access to GPT-style APIs without requiring direct integration with paid official endpoints, focusing on accessibility and ease of experimentation. It offers a proxy-based approach that allows developers to interact with language models through a simplified interface, often requiring minimal configuration. The system is designed to lower barriers for developers who want to test or build applications using conversational AI without managing billing or complex authentication flows. It supports common API formats similar to widely used AI services, making it easier to integrate into existing projects. The project is particularly useful for rapid prototyping, educational purposes, and lightweight applications. It also emphasizes ease of deployment, allowing users to set up and run the service quickly in different environments. -
6
H2O LLM Studio
Framework and no-code GUI for fine-tuning LLMs
Welcome to H2O LLM Studio, a framework and no-code GUI designed for fine-tuning state-of-the-art large language models (LLMs). You can also use H2O LLM Studio with the command line interface (CLI) and specify the configuration file that contains all the experiment parameters. To finetune using H2O LLM Studio with CLI, activate the pipenv environment by running make shell. With H2O LLM Studio, training your large language model is easy and intuitive. First, upload your dataset and then start training your model. Start by creating an experiment. You can then monitor and manage your experiment, compare experiments, or push the model to Hugging Face to share it with the community. -
7
HumanEval
Code for the paper "Evaluating Large Language Models Trained on Code"
human-eval is a benchmark dataset and evaluation framework created by OpenAI for measuring the ability of language models to generate correct code. It consists of hand-written programming problems with unit tests, designed to assess functional correctness rather than superficial metrics like text similarity. Each task includes a natural language prompt and a function signature, requiring the model to generate an implementation that passes all provided tests. The benchmark has become a standard for evaluating code generation models, including those in the Codex and GPT families. Researchers can use the dataset to run reproducible comparisons across models and track improvements in functional code synthesis. By focusing on correctness through execution, human-eval provides a rigorous and practical way to evaluate programming capabilities in AI systems. -
8
LLM Foundry
LLM training code for MosaicML foundation models
Introducing MPT-7B, the first entry in our MosaicML Foundation Series. MPT-7B is a transformer trained from scratch on 1T tokens of text and code. It is open source, available for commercial use, and matches the quality of LLaMA-7B. MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention at a cost of ~$200k. Large language models (LLMs) are changing the world, but for those outside well-resourced industry labs, it can be extremely difficult to train and deploy these models. This has led to a flurry of activity centered on open-source LLMs, such as the LLaMA series from Meta, the Pythia series from EleutherAI, the StableLM series from StabilityAI, and the OpenLLaMA model from Berkeley AI Research. -
9
LLM Telegram Bot
A Telegram bot for Large Language Models
LLM Telegram Bot is a self-hosted Telegram chatbot that connects messaging interactions with large language models, typically powered by Ollama or similar backends. The project is designed to provide a customizable AI assistant that can operate within Telegram conversations, supporting dynamic responses based on user input and configurable parameters. It includes features such as conversation memory, allowing the bot to maintain context across multiple messages and provide more coherent responses. The system supports multiple modes or personas, enabling users to switch between different conversational styles or use cases. It also allows fine-tuning of generation parameters such as temperature and token limits, giving users control over response behavior. The architecture is modular, making it easy to extend or adapt for different workflows or integrations. -
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
10
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training
MedicalGPT training medical GPT model with ChatGPT training pipeline, implementation of Pretraining, Supervised Finetuning, Reward Modeling and Reinforcement Learning. MedicalGPT trains large medical models, including secondary pre-training, supervised fine-tuning, reward modeling, and reinforcement learning training. -
11
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. -
12
MobileLLM
MobileLLM Optimizing Sub-billion Parameter Language Models
MobileLLM is a lightweight large language model (LLM) framework developed by Facebook Research, optimized for on-device deployment where computational and memory efficiency are critical. Introduced in the ICML 2024 paper “MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases”, it focuses on delivering strong reasoning and generalization capabilities in models under one billion parameters. The framework integrates several architectural innovations—SwiGLU activation, deep and thin network design, embedding sharing, and grouped-query attention (GQA)—to achieve a superior trade-off between model size, inference speed, and accuracy. MobileLLM demonstrates remarkable performance, with the 125M and 350M variants outperforming previous state-of-the-art models of the same scale by up to 4.3% on zero-shot commonsense reasoning tasks. -
13
NBA Sports Betting Machine Learning
NBA sports betting using machine learning
NBA-Machine-Learning-Sports-Betting is an open-source Python project that applies machine learning techniques to predict outcomes of National Basketball Association games for analytical and betting-related research. The system gathers historical team statistics and game data spanning multiple seasons, beginning with the 2007–2008 NBA season and continuing through the present. Using this dataset, the project constructs matchup features that represent team performance trends and contextual information about each game. Machine learning models are then trained to estimate the probability that a team will win a game as well as whether the total score will fall above or below the sportsbook’s predicted total. In addition to predicting outcomes, the project evaluates expected value to determine whether a potential bet offers a statistical advantage compared with sportsbook odds. -
14
OmniBox
Collect, organize, use, and share, all in OmniBox
Omnibox (mirror) is a SourceForge mirror of the Omnibox open-source project, which provides a software interface designed to simplify interaction with multiple tools and services through a unified command or search interface. The project focuses on creating a centralized input field where users can enter commands, queries, or shortcuts that trigger actions across different applications or services. Inspired by the omnibox concept used in modern browsers, the system combines search functionality with command execution so that users can access information and perform tasks without navigating complex menus. The mirrored distribution on SourceForge exists to provide an additional download source and preserve access to the software’s source code independent of its original repository. Tools like Omnibox typically emphasize extensibility, allowing developers to add plugins or integrations that connect the interface to other systems such as APIs, search engines, or automation tools. -
15
Qwen-Audio
Chat & pretrained large audio language model proposed by Alibaba Cloud
Qwen-Audio is a large audio-language model developed by Alibaba Cloud, built to accept various types of audio input (speech, natural sounds, music, singing) along with text input, and output text. There is also an instruction-tuned version called Qwen-Audio-Chat which supports conversational interaction (multi-round), audio + text input, creative tasks and reasoning over audio. It uses multi-task training over many different audio tasks (30+), and achieves strong multi-benchmarks performance without task-specific fine‐tuning. It includes features such as flexible multi-run chat, audio understanding/reasoning, music appreciation, and also tool usage (e.g. voice editing). -
16
Qwen3-Omni
Qwen3-omni is a natively end-to-end, omni-modal LLM
Qwen3-Omni is a natively end-to-end multilingual omni-modal foundation model that processes text, images, audio, and video and delivers real-time streaming responses in text and natural speech. It uses a Thinker-Talker architecture with a Mixture-of-Experts (MoE) design, early text-first pretraining, and mixed multimodal training to support strong performance across all modalities without sacrificing text or image quality. The model supports 119 text languages, 19 speech input languages, and 10 speech output languages. It achieves state-of-the-art results: across 36 audio and audio-visual benchmarks, it hits open-source SOTA on 32 and overall SOTA on 22, outperforming or matching strong closed-source models such as Gemini-2.5 Pro and GPT-4o. To reduce latency, especially in audio/video streaming, Talker predicts discrete speech codecs via a multi-codebook scheme and replaces heavier diffusion approaches. -
17
Rogue
AI Agent Evaluator & Red Team Platform
Rogue is an open-source evaluation and red-team framework designed to test the reliability, safety, and policy compliance of AI agents. The platform automatically interacts with an AI agent by generating dynamic scenarios and multi-turn conversations that simulate real-world interactions. Instead of relying solely on static test scripts, Rogue uses an agent-as-a-judge architecture where one agent probes another agent to detect failures or unexpected behaviors. The system allows developers to define specific scenarios, expected outcomes, and business rules so that the framework can verify whether an agent behaves according to required policies. During testing, Rogue records conversations and produces detailed reports that explain whether the agent passed or failed each scenario. These reports include reasoning and evidence, helping developers understand why a particular failure occurred. -
18
Strix
Open-source AI hackers to find and fix your app’s vulnerabilities
Strix is an open source agent-driven security platform that uses autonomous AI agents to identify, investigate, and validate vulnerabilities in software applications. The system is designed to mimic the behavior of real attackers by executing dynamic testing and verifying findings through proof-of-concept exploitation. Unlike traditional vulnerability scanners that rely heavily on static analysis, Strix agents actively run code, probe systems, and attempt exploitation to confirm whether vulnerabilities are genuinely exploitable. The platform is intended for developers and security teams that need rapid security assessments without the overhead of manual penetration testing engagements. Strix can orchestrate multiple cooperating agents that divide investigation tasks and collaboratively analyze complex applications or infrastructure. -
19
VisualGLM-6B
Chinese and English multimodal conversational language model
VisualGLM-6B is an open-source multimodal conversational language model developed by ZhipuAI that supports both images and text in Chinese and English. It builds on the ChatGLM-6B backbone, with 6.2 billion language parameters, and incorporates a BLIP2-Qformer visual module to connect vision and language. In total, the model has 7.8 billion parameters. Trained on a large bilingual dataset — including 30 million high-quality Chinese image-text pairs from CogView and 300 million English pairs — VisualGLM-6B is designed for image understanding, description, and question answering. Fine-tuning on long visual QA datasets further aligns the model’s responses with human preferences. The repository provides inference APIs, command-line demos, web demos, and efficient fine-tuning options like LoRA, QLoRA, and P-tuning. It also supports quantization down to INT4, enabling local deployment on consumer GPUs with as little as 6.3 GB VRAM. -
20
python-whatsapp-bot
Build AI WhatsApp Bots with Pure Python
python-whatsapp-bot is an open-source framework that demonstrates how to build AI-powered WhatsApp bots using pure Python and the official WhatsApp Cloud API. The project provides a practical implementation of a messaging automation system using the Flask web framework to handle webhook events and process incoming messages in real time. Developers can configure the bot to receive user messages through the WhatsApp API, route them through application logic, and generate automated responses powered by AI services such as large language models. The repository includes example scripts and project structures that illustrate how to integrate OpenAI or similar AI models into the bot workflow, enabling conversational agents capable of answering questions or performing automated tasks. -
21
Grok-1
Open-source, high-performance Mixture-of-Experts large language model
Grok-1 is a 314-billion-parameter Mixture-of-Experts (MoE) large language model developed by xAI. Designed to optimize computational efficiency, it activates only 25% of its weights for each input token. In March 2024, xAI released Grok-1's model weights and architecture under the Apache 2.0 license, making them openly accessible to developers. The accompanying GitHub repository provides JAX example code for loading and running the model. Due to its substantial size, utilizing Grok-1 requires a machine with significant GPU memory. The repository's MoE layer implementation prioritizes correctness over efficiency, avoiding the need for custom kernels. This is a full repo snapshot ZIP file of the Grok-1 code. -
22
AReal
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible
AReaL is an open source, fully asynchronous reinforcement learning training system. AReal is designed for large reasoning and agentic models. It works with models that perform reasoning over multiple steps, agents interacting with environments. It is developed by the AReaL Team at Ant Group (inclusionAI) and builds upon the ReaLHF project. Release of training details, datasets, and models for reproducibility. It is intended to facilitate reproducible RL training on reasoning / agentic tasks, supporting scaling from single nodes to large GPU clusters. It can streamline the development of AI agents and reasoning systems. Support for algorithm and system co-design optimizations (to improve efficiency and stability). -
23
Advanced RAG Techniques
Advanced techniques for RAG systems
Advanced RAG Techniques is a comprehensive collection of tutorials and implementations focused on advanced Retrieval-Augmented Generation (RAG) systems. It is designed to help practitioners move beyond basic RAG setups and explore techniques that improve retrieval quality, context construction, and answer robustness. The repository organizes techniques into categories such as foundational RAG, query enhancement, context enrichment, and advanced retrieval, making it easier to navigate specific areas of interest. It includes hands-on Jupyter notebooks and runnable scripts that show how to implement ideas like optimizing chunk sizes, proposition chunking, HyDE/HyPE query transformations, fusion retrieval, reranking, and ensemble retrieval. There is also an evaluation section that demonstrates how to measure RAG performance and compare different configurations in a systematic way. -
24
AudioMuse-AI
AudioMuse-AI is an Open Source Dockerized environment
AudioMuse-AI is an open-source system designed to automatically generate playlists and analyze music libraries using artificial intelligence and audio signal processing techniques. The platform runs locally in a Dockerized environment and performs detailed sonic analysis on audio files to understand characteristics such as tempo, mood, and acoustic similarity. By analyzing the underlying audio content rather than relying on external metadata services, the system can organize large personal music libraries and generate curated playlists for different moods or listening contexts. AudioMuse-AI integrates with several popular self-hosted music servers including Jellyfin, Navidrome, and Emby, allowing users to extend existing media servers with advanced AI-powered recommendation capabilities. The system uses machine learning and audio analysis tools such as Librosa and ONNX models to extract features directly from audio tracks. -
25
BERTopic
Leveraging BERT and c-TF-IDF to create easily interpretable topics
BERTopic is a topic modeling technique that leverages transformers and c-TF-IDF to create dense clusters allowing for easily interpretable topics whilst keeping important words in the topic descriptions. BERTopic supports guided, supervised, semi-supervised, manual, long-document, hierarchical, class-based, dynamic, and online topic modeling. It even supports visualizations similar to LDAvis! Corresponding medium posts can be found here, here and here. For a more detailed overview, you can read the paper or see a brief overview. After having trained our BERTopic model, we can iteratively go through hundreds of topics to get a good understanding of the topics that were extracted. However, that takes quite some time and lacks a global representation. Instead, we can visualize the topics that were generated in a way very similar to LDAvis. By default, the main steps for topic modeling with BERTopic are sentence-transformers, UMAP, HDBSCAN, and c-TF-IDF run in sequence.
