Open Source Python Large Language Models (LLM) - Page 6
Sort By:
Python Large Language Models (LLM)
View 366 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.
-
AestheticsPro Medical Spa SoftwareAestheticsPro is the most complete Aesthetics Software on the market today. HIPAA Cloud Compliant with electronic charting, integrated POS, targeted marketing and results driven reporting; AestheticsPro delivers the tools you need to manage your medical spa business. It is our mission To Provide an All-in-One Cutting Edge Software to the Aesthetics Industry.
-
Process Street | Compliance Operations PlatformBring compliance and operations under one roof with an AI agent that automates workflows, policies that enforce rules, and a platform that delivers results.
-
1
Streamer-Sales
LLM Large Model of Selling Anchor
Streamer-Sales is an open-source large language model system designed specifically for e-commerce live streaming and automated product promotion. The project focuses on generating persuasive product descriptions and live presentation scripts that mimic the style of professional online sales hosts. By analyzing product characteristics and marketing information, the model can produce engaging explanations that emphasize benefits, features, and emotional appeal to encourage viewers to make purchasing decisions. The system integrates multiple AI technologies including retrieval-augmented generation to incorporate product knowledge, speech synthesis to convert generated scripts into voice output, and digital human generation to create virtual hosts. It also supports automatic speech recognition and agent-based tools that can retrieve additional information such as logistics or product details during live sessions. -
2
VALL-E
PyTorch implementation of VALL-E (Zero-Shot Text-To-Speech)
We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called VALL-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that VALL-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find VALL-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis. -
3
Vanna 2.0
Chat with your SQL database
Vanna is an open-source Python framework that enables natural language interaction with databases by converting user questions into executable SQL queries using large language models. The framework uses a retrieval-augmented generation architecture that learns from database schemas, documentation, and past query examples to generate accurate queries tailored to a specific dataset. Vanna can be integrated into many environments, including notebooks, web applications, messaging platforms, and data dashboards, making it flexible for analytics and data exploration workflows. The system streams query results, visualizations, and summaries directly to user interfaces, allowing non-technical users to interact with complex data systems through conversational queries. It also includes enterprise-grade features such as user-aware security, permission enforcement, and query auditing for production deployments. -
4
Xtuner
A Next-Generation Training Engine Built for Ultra-Large MoE Models
Xtuner is a large-scale training engine designed for efficient training and fine-tuning of modern large language models, particularly mixture-of-experts architectures. The framework focuses on enabling scalable training for extremely large models while maintaining efficiency across distributed computing environments. Unlike traditional 3D parallel training strategies, XTuner introduces optimized parallelism techniques that simplify scaling and reduce system complexity when training massive models. The engine supports training models with hundreds of billions of parameters and enables long-context training with sequence lengths reaching tens of thousands of tokens. Its architecture incorporates memory-efficient optimizations that allow researchers to train large models even when computational resources are limited. XTuner is also designed to integrate with modern AI ecosystems, supporting multimodal training, reinforcement learning optimization, and instruction tuning pipelines. -
Cloudbrink Personal SASE serviceCloudbrink’s Personal SASE is a high-performance connectivity and security service that delivers a lightning-fast, in-office experience to the modern hybrid workforce anywhere. Combining high-performance ZTNA with Automated Moving Target Defense (AMTD), and Personal SD-WAN all connections are ultra-secure.
-
5
how-to-optim-algorithm-in-cuda
How to optimize some algorithm in cuda
how-to-optim-algorithm-in-cuda is an open educational repository focused on teaching developers how to optimize algorithms for high-performance execution on GPUs using CUDA. The project combines technical notes, code examples, and practical experiments that demonstrate how common computational kernels can be optimized to improve speed and memory efficiency. Instead of presenting only theoretical explanations, the repository includes hand-written CUDA implementations of fundamental operations such as reductions, element-wise computations, softmax, and attention mechanisms. These examples show how different optimization techniques influence performance on modern GPU hardware and allow readers to experiment with real implementations. The repository also contains extensive learning notes that summarize CUDA programming concepts, GPU architecture details, and performance engineering strategies. -
6
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. -
7
tiny-llm
A course of learning LLM inference serving on Apple Silicon
tiny-llm is an educational open-source project designed to teach system engineers how large language model inference and serving systems work by building them from scratch. The project is structured as a guided course that walks developers through the process of implementing the core components required to run a modern language model, including attention mechanisms, token generation, and optimization techniques. Rather than relying on high-level machine learning frameworks, the codebase uses mostly low-level array and matrix manipulation APIs so that developers can understand exactly how model inference works internally. The project demonstrates how to load and run models such as Qwen-style architectures while progressively implementing performance improvements like KV caching, request batching, and optimized attention mechanisms. It also introduces concepts behind modern LLM serving systems that resemble simplified versions of production inference engines such as vLLM. -
8
uqlm
Uncertainty Quantification for Language Models, is a Python package
UQLM is a Python library developed to detect hallucinations and quantify uncertainty in the outputs of large language models. The system implements a variety of uncertainty quantification techniques that assign confidence scores to model responses. These scores help developers determine how likely a generated answer is to contain errors or fabricated information. The library includes both black-box and white-box approaches to uncertainty estimation. Black-box methods evaluate model outputs through multiple generations or comparative analysis, while white-box methods rely on token probabilities produced during inference. UQLM also supports ensemble strategies and model-as-judge approaches for evaluating responses. By combining multiple uncertainty metrics, the system provides more reliable indicators of when language model outputs may be unreliable. -
9
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. -
TelemetryTV content management and device management<section class="row"> <div class="small-12 columns"> <p class="description">TelemetryTV is a powerful digital signage platform built for the modern communicator who needs to engage audiences, generate awareness, or give their community a voice. TelemetryTV allows users to broadcast dynamic content easily by streaming video, images, social feeds, turnkey apps, and data-driven dashboards to all of your displays wherever they are. TelemetryTV powers marketing and internal communications at Starbucks, New York Public Library, Stanford University, and more.</p> </div> </section>
-
10
Aviary
Ray Aviary - evaluate multiple LLMs easily
Aviary is an LLM serving solution that makes it easy to deploy and manage a variety of open source LLMs. Providing an extensive suite of pre-configured open source LLMs, with defaults that work out of the box. Supporting Transformer models hosted on Hugging Face Hub or present on local disk. Aviary has native support for autoscaling and multi-node deployments thanks to Ray and Ray Serve. Aviary can scale to zero and create new model replicas (each composed of multiple GPU workers) in response to demand. Ray ensures that the orchestration and resource management is handled automatically. Aviary is able to support hundreds of replicas and clusters of hundreds of nodes, deployed either in the cloud or on-prem. -
11
Bard API
The unofficial python package that returns response of Google Bard
The Python package returns a response of Google Bard through the value of the cookie. This package is designed for application to the Python package ExceptNotifier and Co-Coder. Please note that the bardapi is not a free service, but rather a tool provided to assist developers with testing certain functionalities due to the delayed development and release of Google Bard's API. It has been designed with a lightweight structure that can easily adapt to the emergence of an official API. Therefore, I strongly discourage using it for any other purposes. If you have access to official PaLM-2 API, replace the provided response with the corresponding official code. -
12
Bespoke Curator
Synthetic data curation for post-training and data extraction
Curator is an open-source Python library designed to build synthetic data pipelines for training and evaluating machine learning models, particularly large language models. The system helps developers generate, transform, and curate high-quality datasets by combining automated generation with structured validation and filtering. It supports workflows where models are used to produce synthetic examples that can later be refined into reliable training datasets for reasoning, question answering, or structured information extraction tasks. Curator includes tools for monitoring data generation processes and managing dataset quality while large batches of examples are being created. The framework also integrates with multiple inference systems and APIs, allowing users to generate data using different model providers or open-source inference engines. -
13
Claude Code Bridge
Real-time multi-AI collaboration: Claude, Codex & Gemini
Claude Code Bridge is an open-source command-line tool designed to enable real-time collaboration between multiple AI coding assistants within a unified development environment. The system allows developers to coordinate interactions between models such as Claude, Codex, and Gemini so that they can work together on programming tasks. By maintaining persistent shared context between these models, the tool reduces redundant prompts and minimizes token usage while allowing each AI system to contribute specialized capabilities. The architecture functions as a unified launcher that manages communication between multiple AI providers and coordinates their responses within the same development session. Developers can run the tool in terminal environments and integrate it with terminal multiplexers such as tmux or advanced terminal emulators. -
14
CodeGeeX2
CodeGeeX2: A More Powerful Multilingual Code Generation Model
CodeGeeX2 is the second-generation multilingual code generation model from ZhipuAI, built upon the ChatGLM2-6B architecture and trained on 600B code tokens. Compared to the first generation, it delivers a significant boost in programming ability across multiple languages, outperforming even larger models like StarCoder-15B in some benchmarks despite having only 6B parameters. The model excels at code generation, translation, summarization, debugging, and comment generation, and it supports over 100 programming languages. With improved inference efficiency, quantization options, and multi-query/flash attention, CodeGeeX2 achieves faster generation speeds and lightweight deployment, requiring as little as 6GB GPU memory at INT4 precision. Its backend powers the CodeGeeX IDE plugins for VS Code, JetBrains, and other editors, offering developers interactive AI assistance with features like infilling and cross-file completion. -
15
CodeLlama
Inference code for CodeLlama models
Code Llama is a family of Llama-based code models optimized for programming tasks such as code generation, completion, and repair, with variants specialized for base coding, Python, and instruction following. The repo documents the sizes and capabilities (e.g., 7B, 13B, 34B) and highlights features like infilling and large input context to support real IDE workflows. It targets both general software synthesis and language-specific productivity, offering strong performance among open models at release time. Typical usage includes prompt-driven generation, function or class completion, and zero-shot adherence to natural-language instructions about code changes. The ecosystem provides multiple distributions (e.g., HF format) so developers can integrate with standard toolchains and serving stacks. As part of the broader Llama effort, Code Llama complements instruction-tuned chat models by focusing on code-centric tasks and editor integrations. -
16
EmoLLM
Pre & Post-training & Dataset & Evaluation & Depoly & RAG
EmoLLM is an open-source family of large language models focused on mental health support and counseling-oriented interactions. The project is designed to help users through mental health conversations and has been fine-tuned from existing instruction-following LLMs rather than built as a base model from scratch. Its repository includes multiple model variants and training configurations spanning several underlying model families, including InternLM, Qwen, DeepSeek, Mixtral, LLaMA, and others, which shows that the initiative is structured as a broad ecosystem rather than a single release. The project also covers more than just model weights, with material for datasets, fine-tuning, evaluation, deployment, demos, RAG, and related subprojects such as its psychological digital assistant work. -
17
FuzzyAI Fuzzer
A powerful tool for automated LLM fuzzing
FuzzyAI is an open-source fuzzing framework designed to test the security and reliability of large language model applications. The tool automates the process of generating adversarial prompts and input variations to identify vulnerabilities such as jailbreaks, prompt injections, or unsafe model responses. It allows developers and security researchers to systematically evaluate the robustness of LLM-based systems by simulating a wide range of malicious or unexpected inputs. The framework can be integrated into development pipelines to continuously test AI APIs and detect weaknesses before deployment. FuzzyAI provides testing tools, datasets, and evaluation workflows that help researchers measure how well models resist harmful instructions or attempts to bypass safety mechanisms. -
18
GLM-4-Voice
GLM-4-Voice | End-to-End Chinese-English Conversational Model
GLM-4-Voice is an open-source speech-enabled model from ZhipuAI, extending the GLM-4 family into the audio domain. It integrates advanced voice recognition and generation with the multimodal reasoning capabilities of GLM-4, enabling smooth natural interaction via spoken input and output. The model supports real-time speech-to-text transcription, spoken dialogue understanding, and text-to-speech synthesis, making it suitable for conversational AI, virtual assistants, and accessibility applications. GLM-4-Voice builds upon the bilingual strengths of the GLM architecture, supporting both Chinese and English, and is designed to handle long-form conversations with context retention. The repository provides model weights, inference demos, and setup instructions for deploying speech-enabled AI systems. -
19
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. -
20
Gemini Fullstack LangGraph Quickstart
Get started w/ building Fullstack Agents using Gemini 2.5 & LangGraph
gemini-fullstack-langgraph-quickstart is a fullstack reference application from Google DeepMind’s Gemini team that demonstrates how to build a research-augmented conversational AI system using LangGraph and Google Gemini models. The project features a React (Vite) frontend and a LangGraph/FastAPI backend designed to work together seamlessly for real-time research and reasoning tasks. The backend agent dynamically generates search queries based on user input, retrieves information via the Google Search API, and performs reflective reasoning to identify knowledge gaps. It then iteratively refines its search until it produces a comprehensive, well-cited answer synthesized by the Gemini model. The repository provides both a browser-based chat interface and a command-line script (cli_research.py) for executing research queries directly. For production deployment, the backend integrates with Redis and PostgreSQL to manage persistent memory, streaming outputs, & background task coordination. -
21
Hephaestus
Semi-Structured Agentic Framework. Workflows build themselves
Hephaestus is an open-source semi-structured agentic framework designed to orchestrate multiple AI agents working together on complex tasks. Instead of relying entirely on predefined workflows, the framework allows agents to dynamically create tasks as they explore a problem space. Developers define high-level phases such as analysis, implementation, and testing, while agents generate specific subtasks within those phases. The system continuously monitors agent behavior and task progression, allowing workflows to evolve as new discoveries are made. For example, if an agent detects a bug or optimization opportunity, it can automatically create a new task and integrate it into the workflow. The framework also includes monitoring mechanisms that track agent trajectories and ensure that tasks remain aligned with overall objectives. -
22
Huatuo-Llama-Med-Chinese
Instruction-tuning LLM with Chinese Medical Knowledge
Huatuo-Llama-Med-Chinese is an open-source project that develops medical-domain large language models by instruction-tuning existing models using Chinese medical knowledge. The project builds specialized models by fine-tuning architectures such as LLaMA, Alpaca-Chinese, and Bloom with curated medical datasets. These datasets are constructed from medical knowledge graphs, academic literature, and question-answer pairs designed to teach models how to respond accurately to healthcare-related queries. The goal of the project is to improve the reliability and domain expertise of language models when answering medical questions or assisting with healthcare-related tasks. By combining domain-specific training data with instruction-tuning techniques, the project produces models capable of generating more accurate medical responses than general-purpose models. -
23
HuixiangDou
Overcoming Group Chat Scenarios with LLM-based Technical Assistance
HuixiangDou is an open-source large language model assistant designed specifically for technical question answering in group chat environments. The project addresses a common problem in developer communities where discussion channels become overwhelmed by repeated or irrelevant questions. To solve this issue, HuixiangDou implements a multi-stage pipeline that analyzes incoming messages, filters irrelevant conversations, and selectively generates responses when the assistant determines it can provide useful information. This design allows the system to participate in group discussions without flooding the chat with unnecessary messages. The assistant uses retrieval and ranking methods along with language model reasoning to produce accurate answers for technical topics such as computer vision and machine learning projects. It can be integrated into messaging platforms such as WeChat or other team collaboration tools to assist developer communities. -
24
Index
The SOTA Open-Source Browser Agent
Index is an open-source browser automation agent designed to autonomously perform complex tasks across websites by transforming web interfaces into programmable APIs. The system enables developers to instruct an AI agent to interact with web pages using natural language rather than traditional automation scripts. Instead of writing detailed browser automation code, users can describe the desired task and allow the agent to interpret the page structure, interact with elements, and complete multi-step workflows automatically. The project is built to integrate easily with applications through a simple programming interface, allowing developers to embed browser automation capabilities directly into their software systems. Index can perform tasks such as navigating pages, filling forms, collecting data, and analyzing web content without requiring manual scripting for each website. -
25
Integuru v0
The first AI agent that builds permissionless integrations
Integuru is an open-source AI agent designed to automatically create integrations between software platforms by reverse-engineering their internal APIs. Instead of relying on official developer documentation or publicly available APIs, the system analyzes network traffic generated by user interactions within a web application. Developers capture browser requests and authentication data, which the agent then uses to infer the structure of the platform’s internal API endpoints. Based on this information, the system generates executable code that can replicate the original action programmatically. This approach allows developers to automate workflows and build integrations with services that do not provide official APIs or developer tools. The project is designed as a research platform for exploring AI-driven automation and integration generation.
