banner
Orion-14B

Born for Enterprise Applications

Born for Enterprise Applications

Effective, Affordable, Reliable
Apply for
Experience Now
Newly Released Orion-14B Base Model

Newly Released Orion-14B Base Model
Evaluation Metrics
OrionStar Open-Source Multilingual Large Language Model,Orion-14BEvaluation Metrics
Based on the independent evaluation results from the third-party agency OpenCompass.
Multiple Language Test Scores
OrionStar Open-Source Multilingual Large Language Model Evaluation Metrics
Performance Highlights
Rival hundred-billion-parameter models
The 14B LLM, a medium-scale model, achieves state-of-the-art performance comparable to models below 20B.
Support 320K ultra-long context
Support extremely long texts, performing exceptionally well at a token length of 200k and can support up to a maximum of 320k.
The optimal LLM choice for enterprises
  • Orion-14B series fine-tuned LLM, adaptable to various scenarios
  • Performance loss after INT4 quantized is less than 1%
    Strong multilingual capabilities
    Ranked first in evaluations for Chinese, English, Japanese, and Korean among models with parameters below 20B.
    Technical Advantages
    Top Team
    Top Team
    More than a hundred top algorithm scientists from global tech giants such as Facebook, Yahoo, Baidu, and more.
    Algorithm Mastery
    Algorithm Mastery
    Our technical roadmap encompasses DNN, attention, Bert, LLM, ASR, TTS, NLP, tracking the industry's technological evolution comprehensively.
    Scene Understanding
    Scene Understanding
    Adapted for applications in over a thousand enterprises.
    Application Refinement
    Application Refinement
    Extensive experience in refining applications for a user base of 2 billion globally.
    Data Accumulation
    Data Accumulation
    Accumulated real user query data in the tens of billions and token data in several tens of trillion over nearly 7 years.
    Highly Effective Enterprise-Application LLM Orion-14B series fine-tuned large language models:
    professional scenario capabilities, state-of-the-art ten-billion-parameter models
    General dialogue fine-tuning
    General dialogue fine-tuning
    Among open-source multilingual large language models below 20B, the best-performing general dialogue model.
    Plugin fine-tuning
    Plugin fine-tuning
    Enhanced capabilities in Agent, ReAct, and Prompting, delivering results close to a hundred billion parameter models.
    RAG fine-tuning
    RAG fine-tuning
    Knowledge boundary control, precision in answers, achieving effects similar to trillion-parameter models.
    Long Token fine-tuning
    Long Token fine-tuning
    Supports tokens of up to 320K in length, the best among open-source models in token support.
    Knowledge extraction fine-tuning
    Knowledge extraction fine-tuning
    Transforms unstructured data into structured data.
    Question-Answer Pair Generation fine-tuning
    Question-Answer Pair Generation fine-tuning
    Generates question-answer pairs while ensuring comprehensive knowledge coverage.
    Japanese and Korean fine-tuning
    Japanese and Korean fine-tuning
    Optimal performance in Japanese and Korean languages among open-source models below 20B.
    Orion-14B Large Language Model
    Affordable LLM for Enterprise Applications
    Suitable for Enterprise Use
    Suitable for Enterprise Use
    After INT4 quantization, the model size is reduced by 70%, inference speed is increased by 30%, with less than 1% performance loss
    Run on Affordable Graphics Cards
    Run on Affordable Graphics Cards
    Such as NVIDIA RTX 3060, capable of achieving 31 tokens per second, approximately 100 characters
    <span>Affordable</span> LLM for Enterprise Applications
    Affordable LLM for Enterprise Applications
    Suitable for Enterprise Use
    Suitable for Enterprise Use
    After INT4 quantization, the model size is reduced by 70%, inference speed is increased by 30%, with less than 1% performance loss
    Run on Affordable Graphics Cards
    Run on Affordable Graphics Cards
    Such as NVIDIA RTX 3060, capable of achieving 31 tokens per second, approximately 100 characters
    <span>Affordable</span> LLM for Enterprise Applications
    Reliable LLM for Enterprise Applications
    Private Deployment
    Private Deployment
    Large model servers can be situated within the enterprise intranet, ensuring all data does not connect to the public internet.
    Free, Open Source, and Commercially Usable with Community Technical Support
    Free, Open Source, and Commercially Usable with Community Technical Support
    Available for download from communities such as Hugging Face and GitHub.
    <span>Reliable</span> LLM for Enterprise Applications