Filters

AI Models

BabyAGIOpenAIGPT-3.5SuperAGIClarifaiStableCodeGrounded-Segment-AnythingprivateGPTGenerative AgentsChatGPTWeaviateGenerative AI StudioOpenAI gymAudioCraftLlamaIndexPaLMDall-e MiniGPT-3CodexYOLOv7BERTYOLOv5GANReinforcement LearningAWS SageMakerEasyOCRCAMELText Generation Web UIShap-EDALL-E-2AI21 LabsCohere EmbedChirpWhisperStable DiffusionWebGPUMonday AI AssistantMonday.comChromaCohere GenerateCohere ClassifyGPT-4AlpacaLLaMAAuto-GPTAnthropic ClaudeYOLOv8gpt4allFalconCodeyModel GardenElevenLabsLlama 2Point-EGET3DStable DreamfusionSeamlessM4TLangChainCohere

Data

RedisQdrant

Platforms

StreamlitReplitVercel

LlamaIndex Applications

Browse applications built on LlamaIndex technology. Explore PoC and MVP applications created by our community and discover innovative use cases for LlamaIndex technology.

AllTrending 🚀Recent Winners 🥇Most votes 🔝

ELIZA EVOL INSTRUCT - Fine-Tuning

We attempted to instill the deterministic, rule-based reasoning found in ELIZA into a more advanced, probabilistic model like an LLM. This serves a dual purpose: To introduce a controlled variable in the form of ELIZA's deterministic logic into the more "fuzzy" neural network-based systems. To create a synthetic dataset that can be used for various Natural Language Processing (NLP) tasks, beyond fine-tuning the LLM. [ https://huggingface.co/datasets/MIND-INTERFACES/ELIZA-EVOL-INSTRUCT ] [ https://www.kaggle.com/code/wjburns/pippa-filter/ ] ELIZA Implementation: We implemented the script meticulously retaining its original transformational grammar and keyword matching techniques. Synthetic Data Generation: ELIZA then generated dialogues based on a seed dataset. These dialogues simulated both sides of a conversation and were structured to include the reasoning steps ELIZA took to arrive at its responses. Fine-tuning: This synthetic dataset was then used to fine-tune the LLM. The LLM learned not just the structure of human-like responses but also the deterministic logic that went into crafting those responses. Validation: We subjected the fine-tuned LLM to a series of tests to ensure it had successfully integrated ELIZA's deterministic logic while retaining its ability to generate human-like text. Challenges Dataset Imbalance: During the process, we encountered issues related to data imbalance. Certain ELIZA responses occurred more frequently in the synthetic dataset, risking undue bias. We managed this through rigorous data preprocessing. Complexity Management: Handling two very different types of language models—rule-based and neural network-based—posed its unique set of challenges. Significance This project offers insights into how the strength of classic models like ELIZA can be combined with modern neural network-based systems to produce a model that is both logically rigorous and contextually aware.

MIND INTERFACES
LlamaIndexLlama 2

OS-Chat

Open Source Chat: Revolutionizing Open-Source Knowledge Accessibility The Inspiration Behind Open Source Chat The idea for Open Source Chat was born out of the recognition that many software programmers and developers face the same challenge—navigating and extracting valuable insights from open-source documentation. It's a challenge that can slow down development processes, hinder innovation, and lead to frustration. The team behind Open Source Chat recognized this pain point and was inspired to create a solution that would streamline the process, making open-source knowledge readily available to all. The inspiration for Open Source Chat comes from a deep appreciation for the open-source community and the immense contributions it has made to the world of technology. Open-source software powers everything from web servers to mobile applications to scientific research. It's a collective effort that has transformed industries and empowered individuals and organizations around the globe.

Nas
Streamlit
application badge
OpenAIGPT-3.5FineTuner.aiClarifaiLangChainLlamaIndexWeaviateSeamlessM4T

Fun with my friend JARVIS

Introduction Welcome to the World of Crafting Your Own Voice Wizard 🎙️ The concept is a personalized voice assistant that bridges the gap between humans and technology using voice-text transformation with Python and the Llama API. This is a highlight to unveil the secrets behind creating an interactive and enchanting Jarvis-like assistant. Voice Recognition (Listen for Command) The Art of Casting Spells with Your Voice 🎶 Explore the wonder of voice to text and back again using Llama API as it transforms spoken words into written commands and then back to speech again. Explore and share with friends how the "listen_for_command" method creates a magical bridge between user voice and digital interaction, bringing the assistant to life. Text-to-Speech (Generating Responses with Llama) Transforming Whispers into Majestic Speech 📣 Dive into the enchanting process of converting text into lifelike speech with the Llama API. Illustrate how the "text_to_speech" method weaves text into captivating auditory experiences, adding a personalized touch to interactions. Highlight the synthesis of natural-sounding voices, bringing forth an auditory dimension that connects users with their digital companion. Enhancements and Extensions Elevate and extend your assistant's capabilities beyond voice recognition and synthesis by teasing out the limitless possibilities: from controlling devices with voice commands to infusing emotional intelligence into speech. Conclusion The transformative power of Llama API and Python create a seamless human-computer interaction and makes a easy and fun to interact with all your devices just by talking to them! Our vision of the future where voice assistants understand context, emotions, and devices, leading to more immersive experiences. We are creating new spells that redefine how we communicate with machines. Thank You and Cheers!

Too much Base
Streamlit
application badge
GPT-3.5AudioCraftLlamaIndex