Search Results for "llama" - Page 5
Sort By:
Showing 118 open source projects for "llama"
View related business solutions-
Propel Software: Product Value Management Platform for ManufacturersPropel is a cloud-native Product Value Management platform that unifies PLM, QMS, and PIM in one connected system, giving manufacturers complete visibility and control across the entire product lifecycle. It provides a single source of truth for all product data, streamlines change management, strengthens quality and compliance processes, and accelerates time-to-market by eliminating the silos and manual steps that slow teams down.
-
Empower Your Contact Center with Human-Like AI ConversationsEnterprise Bot, based in Switzerland, is a pioneer in Conversational AI, Process Automation, and Generative AI. With the trust of esteemed enterprise giants across industries like Generali, SIX, SBB, DHL, and SWICA, Enterprise Bot is revolutionizing both customer and employee experiences. Through its advanced integration with Large Language Models (LLM) such as ChatGPT and Llama 2, and its unique patent-pending DocBrain technology, the company delivers unparalleled personalization, active engagement, and omnichannel solutions across platforms like email, voice, and chat. Furthermore, Enterprise Bot integrates with existing core systems, such as SAP, CRMs, Confluence and more, and with its proprietary middleware, Blitzico, enables the AI to not only respond to queries but also take action to resolve them. This dedication to innovation in four main use case areas, Customer Support, Sales and Marketing, Knowledge Management and Digital Coworker, elevates both CX and employee productivity.
-
1
unit-minions
AI R&D Efficiency Improvement Research: Do-It-Yourself Training LoRA
"AI R&D Efficiency Improvement Research: Do-It-Yourself Training LoRA", including Llama (Alpaca LoRA) model, ChatGLM (ChatGLM Tuning) related Lora training. Training content: user story generation, test code generation, code-assisted generation, text to SQL, text generation code. -
2
pyllama
LLaMA: Open and Efficient Foundation Language Models
📢 pyllama is a hacked version of LLaMA based on original Facebook's implementation but more convenient to run in a Single consumer grade GPU. -
3
Dalai
The simplest way to run LLaMA on your local machine
Run LLaMA and Alpaca on your computer. Dalai runs on all of the following operating systems, Linux, Mac, and Windows. Runs on most modern computers. Unless your computer is very very old, it should work. -
4
Alpaca.cpp
Locally run an Instruction-Tuned Chat-Style LLM
Run a fast ChatGPT-like model locally on your device. This combines the LLaMA foundation model with an open reproduction of Stanford Alpaca a fine-tuning of the base model to obey instructions (akin to the RLHF used to train ChatGPT) and a set of modifications to llama.cpp to add a chat interface. Download the zip file corresponding to your operating system from the latest release. The weights are based on the published fine-tunes from alpaca-lora, converted back into a PyTorch checkpoint with a modified script and then quantized with llama.cpp the regular way. -
ACI Learning: Internal Audit, Cybersecurity, and IT TrainingTraditional training doesn't equip employees with the practical skills they need to drive business success. ACI Learning provides hands-on IT and cybersecurity training designed to build real-world, on-the-job skills. Our outcome-based programs empower employees with certification prep, industry-recognized credentials, and flexible learning options. With expert-led video training, labs, and scalable solutions, we help businesses, individuals, governments, and academic institutions develop a skilled workforce, align with business goals, and stay ahead in a rapidly evolving digital world.
-
5
Nuestro componente se llama “Cronometro”, es un componente el cual muestra en una etiqueta las centésimas de segundo, los segundos, los minutos y las horas transcurridas. Cuenta con los siguientes métodos: Iniciar().- empieza a correr el cronometro. Pausar().-pausa el cronometro (solo funciona si el cronometro ya esta iniciado). Detener().-Detiene el cronometro y los regresa a su estado inicial (solo funciona si el cronometro ya esta iniciado).
-
6
compara el consumo de tu cuenta vodafone
control y de consumo vodafone por detalle de llamadas
Controla y compara el consumo de todas las lineas de tu cuenta vodafone. Visualiza el gasto diario en telefonía. Visualiza el tipo de llamada . Visualiza los destinos a los que se llama. solamente tienes que importar el archivo de detalle de llamadas que te descargas de la página de Vodafone. Podrás visualizar y comparar la información de las líneas con dos click del ratón. La aplicación esta escrita en PHP y usa una base de datos MYSQL. Deberás de extraer el contenido del archivo que te descargues dentro del directorio raíz de tu servidor web (www) después ejecutar el archivo SETUP.sql para crear la base de datos y parametrizar el archivo include_config.php con los datos de conexión a la base de datos. -
7
Llama Alarm Clock
A Simple, easy to use, customizable Alarm Clock
Llama Alarm Clock is a simple, easy to use, alarm clock. You can display a 12 or 24 hour clock and set alarms in either form (they work regardless of your display mode) and plays any .wav media file you choose to wake you up ***NOW SUPPORTS .MP3 FILES*** (Thank you Jake Rooney). It comes with 2 alarms (If you have version 1.3 make sure to use the new default ones). -
8
Llama Stocks
Stock tracking application
A Stock tracking application. IF YOU HAVE AN OLD SAVE.SAV SAVE YOUR INFORMATION AND DELETE IT. IT WILL NOT WORK WITH 1.7. You can track as many symbols as you have monitor space for. Displays Current trading price (+/- from open, +/- % from open), today's high, today's low, yesterday's close, and volume in an easy to read, size adjustable format.You can input the number of shares you own and the price you bought them at and it calculates your current gain/loss in real time. You can set... -
9
Llama Music Cleanser
Cleanses your music folder of all those unwanted songs
...Rating it good leaves it where it is and starts the next song in the folder. Rating it bad moves it to the folder where you put Llama Music Cleanser where you can delete the whole folder in the click of a button (or two). And suddenly, your music collection only has songs you want! ***DOES REQUIRE JAVA 7*** If you do not have Java 7 go to: http://www.oracle.com/technetwork/java/javase/downloads/index.html -
Time tracking software for the global workforceIt's easy with Hubstaff, a time-tracking and workforce management platform that automates almost every aspect of running or growing a business. Teams can track time to projects and to-dos using Hubstaff's desktop, web, or mobile applications. You'll be able to see how much time your team spends on different tasks, plus productivity metrics like activity rates and app usage through Hubstaff's online dashboard. Most of the available features are customizable on a per-user basis, so you can create the team management tool you need.
-
10
LLAMA - stands for LARP MAnager. Web based application, tool to support organization of LARP/RPG games - in phase of game preparation as well as during playing the game.
-
11
Llama CMS: A simple yet powerful CMS. Administer content, news, and polls, members, and themes. LCMS strives to give the website administrator the power to easily control dynamic content while avoiding the prebuilt look of typical portal systems.
-
12
The goal of llama-X is to be a cutting-edge desktop operating system for the x86 architecture. A new object-oriented filesystem, and a fresh new desktop paradigm, and an innovative multikernel subsystem are main features of the system.
-
13
Llama-3.2-1B
Llama 3.2–1B: Multilingual, instruction-tuned model for mobile AI
meta-llama/Llama-3.2-1B is a lightweight, instruction-tuned generative language model developed by Meta, optimized for multilingual dialogue, summarization, and retrieval tasks. With 1.23 billion parameters, it offers strong performance in constrained environments like mobile devices, without sacrificing versatility or multilingual support. -
14
Llama-3.2-1B-Instruct
Instruction-tuned 1.2B LLM for multilingual text generation by Meta
Llama-3.2-1B-Instruct is Meta’s multilingual, instruction-tuned large language model with 1.24 billion parameters, optimized for dialogue, summarization, and retrieval tasks. It builds upon the Llama 3.1 architecture and incorporates fine-tuning techniques like SFT, DPO, and quantization-aware training for improved alignment, efficiency, and safety. -
15
Hermes 4
Hermes 4 FP8: hybrid reasoning Llama-3.1-405B model by Nous Research
Hermes 4 405B FP8 is a cutting-edge large language model developed by Nous Research, built on Llama-3.1-405B and optimized for frontier reasoning and alignment. It introduces a hybrid reasoning mode with explicit <think> segments, enabling the model to deliberate deeply when needed and switch to faster responses when desired. Post-training improvements include a vastly expanded corpus with ~60B tokens, boosting performance across math, code, STEM, logic, creativity, and structured outputs. ... -
16
Mellum-4b-base
JetBrains’ 4B parameter code model for completions
Mellum-4b-base is JetBrains’ first open-source large language model designed and optimized for code-related tasks. Built with 4 billion parameters and a LLaMA-style architecture, it was trained on over 4.2 trillion tokens across multiple programming languages, including datasets such as The Stack, StarCoder, and CommitPack. With a context window of 8,192 tokens, it excels at code completion, fill-in-the-middle tasks, and intelligent code suggestions for professional developer tools and IDEs. ... -
17
OpenVLA 7B
Vision-language-action model for robot control via images and text
...It takes camera images and natural language instructions as input and outputs normalized 7-DoF robot actions, enabling control of multiple robot types across various domains. Built on top of LLaMA-2 and DINOv2/SigLIP visual backbones, it allows both zero-shot inference for known robot setups and parameter-efficient fine-tuning for new domains. The model supports real-world robotics tasks, with robust generalization to environments seen in pretraining. Its actions include delta values for position, orientation, and gripper status, and can be un-normalized based on robot-specific statistics. ... -
18
TARILIO
Advanced Full Text Search + AI Assistant + Local Server for LLMs
...Advanced features: set LLM sampler parameters, scrolling index vocabulary, multilingual stemming, synonyms. MCP Client. UI can be translated using a free Language File Translator. Uses Llama Sharp and Lucene search engine . Open source and free. TARILIO PRO commercial version.
