LogoLogo
NeurochainAI Guides
NeurochainAI Guides
  • Quick Start Guide
  • NeurochainAI Official Links
  • Getting started
    • Understanding the Dashboard
    • Specific FAQs
  • BUILD ON DIN
    • What is Distributed Inference Network (DIN)
      • Why Build on DIN?
      • Introduction to Inference
    • AI Models Available on DIN
    • Adding Credits
    • Generating an API Key for Inference
    • Use Sentiment Analysis
    • Pricing
    • INTEGRATIONS
      • Make (Integromat) - Use IaaS in Your Scenarios
      • N8N - Use IaaS in Your Workflow
      • Typebot - Use IaaS in Your Chatbot
      • Botghost - Creating AI Discord Bots
      • Replit - Building AI-Powered Chatbot
        • Build Custom Solutions with Flux.1 Schnell
      • Pipedream - N8N - Use IaaS in Your Automation
      • Voiceflow - Use IaaS to Enhance Your Chatbot
      • Open API Integration
      • BuildShip - Use IaaS to Automate Workflows
      • Pipefy - Optimizing Business Processes
  • No-code workshops
  • NeurochainAI No-Code: AI Automation with N8N
  • NeurochainAI No-Code: Development Guide (Bolt.new)
  • NeurochainAI No-Code: Build AI-Powered Apps with Cursor
  • NeurochainAI No-Code: Intelligent Text Parsing
  • CONNECT GPUs
    • Connect GPUs: All You Need to Know
    • GPU Setup Instructions
    • Running the Worker
    • Mobile App
  • ENTERPRISE SOLUTIONS
    • Inference Routing Solution
    • Managed Inference Infrastructure
    • AI Model Quantization
    • Data Layer
  • NCN Chain
    • NCN Scan
    • Setting Up Wallet
      • Manual Addition (MetaMask)
    • Trading $NCN on Uniswap
    • Neuron Validator Nodes
      • How to stake
      • Hardware Requirements
      • Running a Neuron Node
  • Community
    • NeurochainAI Loyalty Program
    • All the Ways to Get Involved
Powered by GitBook
On this page
  1. BUILD ON DIN

AI Models Available on DIN

The Distributed Inference Network (DIN) by NeurochainAI provides access to a selection of optimized, high-performance AI models for various applications, including language understanding, instruction following, and specialized tasks.

Below is the current list of AI models available on DIN.


Available Models

  1. Open Llama Series

    • open-llama-3b-v2-instruct-Q8_0-GGUF

    • Meta-Llama-3.1-8B-Instruct-Q8_0.gguf

    • Meta-Llama-3.1-8B-Instruct-Q6_K.gguf

    Description: The Open Llama models are designed for versatile instruction-following tasks and support various applications in natural language understanding and generation.

  2. Mistral Series

    • Mistral-7B-Instruct-v0.2-GPTQ-Neurochain-custom-io

    • Mistral-7B-Instruct-v0.2-GPTQ-Neurochain-custom

    • Mistral-7B-OpenOrca-GPTQ

    • Mistral-7B-Instruct-v0.1-gguf-q8_0.gguf

    • Mistral-7B-Instruct-v0.2-GPTQ

    Description: The Mistral models are specialized for precise instruction-following, with adaptations and custom fine-tuning by NeurochainAI.

  3. Flux Model

    • flux1-schnell-gguf

    Description: Flux1 Schnell is a high-performance model optimized with GGUF for fast, cost-effective inference. This model is suitable for a range of applications where speed and efficiency are essential, benefiting from advanced 8-bit, 6-bit, and 4-bit quantization.

  4. SentimentAI

  • Description: SentimentAI is a NeurochainAI implementation for monitoring sentiment in Telegram group chats and collecting data. It identifies positive, negative, and neutral sentiments within messages, making it a powerful tool for tracking group sentiment and gathering community insights in real time. SentimentAI is ideal for businesses or communities looking to monitor sentiment dynamics effortlessly.

  1. Specialized Models

  • ingredient-extractor-mistral-7b-instruct-v0.1-gguf-q8_0.gguf

Description: A specialized model designed to extract specific information, such as ingredient lists, from text.

PreviousIntroduction to InferenceNextAdding Credits

Last updated 6 months ago