DeepSeek V4 Pro is Live → Try it now.

Model Library/Fireworks AI/DeepSeek V2.5
Fireworks Logo Mark

DeepSeek V2.5

Ready
Deploy on Demand
Fine-tune
accounts/fireworks/models/deepseek-v2p5

    DeepSeek-V2.5 is an upgraded version that combines DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.

    DeepSeek V2.5 API Features

    Fine-tuning

    Docs

    DeepSeek V2.5 can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model

    On-demand Deployment

    Docs

    On-demand deployments allow you to use DeepSeek V2.5 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    9/6/2024
    Kind
    Base model
    Provider
    Fireworks AI
    Hugging Face
    DeepSeek/deepseek-v2p5

    Specification

    Calibrated
    No
    Mixture-of-Experts
    Yes
    Parameters
    235B

    Supported Functionality

    Fine-tuning
    Supported
    Serverless
    Not supported
    Context Length
    32.7k tokens
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported