Submission declined on 18 April 2024 by Crunchydillpickle (talk). This submission's references do not show that the subject qualifies for a Wikipedia article—that is, they do not show significant coverage (not just passing mentions) about the subject in published, reliable, secondary sources that are independent of the subject (see the guidelines on the notability of websites). Before any resubmission, additional references meeting these criteria should be added (see technical help and learn about mistakes to avoid when addressing this issue). If no additional references exist, the subject is not suitable for Wikipedia.
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|
Lollms
editLollms (Lord of Large Language and Multimodal Systems) is a free and open-source tool designed to provide a unified interface for interacting with various large language models and multimodal systems. Developed by ParisNeo, Lollms aims to simplify access and use of these powerful tools for users in different fields. It offers a Python library, a service with a socketio connection, web requests, and a web interface named lollms-webui, which constitutes the main application of the system. Additionally, it provides libraries allowing interaction with this service from several programming languages such as Python, JavaScript, and C++.
History
editLollms was initially created by ParisNeo in April 2023 as GPT4All-Webui, serving as an access interface for "GPT4All," a system for interacting with local LLMs developed by Nomic AI using LLAMA.Cpp. In mai 2023, ParisNeo renamed it Lollms (Lord of Large Language Models) and expanded its capabilities to support various artificial intelligence systems beyond GPT4All. Thus, the architecture of the new tool presents a unique interface and a binding system allowing unified interaction with all supported systems.
Over time, Lollms' compatibility expanded to include multimodal systems as well as remote systems operating with a key, such as OpenAI, MistralAI, Anthropic, Groq, OpenRouter, and private remote systems like VLLM, Litellm, and Ollama. It also supports distributed systems like Petals. As of December 11, 2023, it is officially designated as LoLLMS(with a capital 'S') which is now Lord of Large Language Multimodal Systems, reflecting its broader scope, which now includes voice input and output, image generation, music generation, song generation, and video generation, as well as image input among other multimodalities.
Key Features
edit- Unified Interface: Lollms provides a single interface for interacting with various large language models and multimodal systems, making these tools easier for users to access.
- Multiple Connectivity Options: Users can interact with Lollms via a socketio connection, web requests, or by using a Python, JavaScript, Unreal Engine, C++ library, and other libraries under development.
- Free and Open Source: Lollms is a free tool developed by ParisNeo as a contribution to the open-source community.
- Lollms-WebUI: A web interface for the Lollms system, designed to provide a user-friendly way to access and use various LLM models for a wide range of tasks.
- Remote Nodes: Lollms allows users to use remote text generation servers as their backend instead of local generation. This feature is particularly useful for companies that want to keep their data secure within their own network.
- Personality System on Lollms: A system for creating simulations of conditioned agents to perform specific tasks, allowing for better task execution and better responsiveness to user requirements.
Personalities in Lollms
editOne of the most well-known features of Lollms is its personalities system, which allows for the creation of simulations of conditioned agents to perform specific tasks. A personality in Lollms is a unique set of characteristics and skills assigned to a language model. Each personality is designed to excel in specific areas, thus providing users with a wide range of knowledge and skills.
There are two types of personalities in Lollms:
- Standard personalities: These are personalities described in a config.yaml file that contains conditioning text, a description, and some metadata about the personality.
- Scripted personalities: These are much more complex personalities, consisting of complete Python programs that can use Lollms connections to perform more complex tasks such as interacting with applications, web scraping, connecting to additional services, and performing sequential work like coding, debugging, testing, validating, and documenting, etc.
Examples of personalities available on Lollms include Artbot, Lawyer, Laughter Bot, and LordOfMusic, among others.
Usage
editLollms can be used in several ways:
- As a library to access generation tools, connectors, data scraping tools, etc.
- As a service to use the tool remotely or locally by another application.
Documentation and Community Support
editLollms provides detailed documentation on GitHub at Lollms-webui GitHub. It is a constantly evolving tool, with new features and improvements being added regularly. Lollms also has an active community of users who share their experiences and provide feedback on the tool. As an open-source project, anyone can contribute to its development and improvement.
References
editLollms official website: [1]