VNPT AI Ecosystem

mic
API requests:

    Engine LLM Technical Specifications

    Technical specifications of Engine LLM when provided as a license.

    Architecture and Technology

    Item Specifications
    Model depth (number of layers) From 32 to 100
    Embedding size From 1024 to 12288

    Standard benchmark model performance

    Item Specifications
    VMLU Score of 75 or higher

    Language understanding and generation capability

    Item Specifications
    Context and flow understanding The model can maintain context in conversation
    Coherent and logical text generation Can generate text based on a given format
    Multilingual processing (if any) Can process Vietnamese and English

    Problem-solving capability

    Item Specifications
    Logical reasoning Solve simple problems and puzzles
    Understand and generate code Can generate simple code

    Safety and Ethics

    Item Specifications
    Sensitive content moderation mechanism Yes
    Avoid answering content outside the data scope Yes

    Operational performance

    Item Specifications
    Average response time Depends on length of input and output. Average response time for first token with 1500 tokens input is under 1s
    Scalability Capability to scale across multiple GPU clusters
    Integration with other systems - Provides integration capability via API
    - Capability to integrate RAG for specialized knowledge

    Customization and additional training

    Item Specifications
    Fine-tuning with user data Allows model customization and adding more training text data

    Additional information

    Item Specifications
    Fast training data creation Support building training data by importing Excel files
    Multi-platform chat and internal communication channel integration Facebook, Zalo, Viber, Telegram, Website, and internal communication channels
    Model update and development roadmap Regularly update to new versions. Customers get to use our latest features and models
    User documentation PDF documentation available