lucataco / qwen1.5-14b

Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data

  • Public
  • 720 runs
  • L40S
  • GitHub
  • License
  • Prediction

    lucataco/qwen1.5-14b:28c4bbc1
    ID
    iki4u23boimkrvwprgi4pdy6ai
    Status
    Succeeded
    Source
    Web
    Hardware
    A40 (Large)
    Total duration
    Created

    Input

    top_k
    1
    top_p
    1
    prompt
    Give me a short introduction to large language model.
    temperature
    1
    system_prompt
    You are a helpful assistant.
    max_new_tokens
    512
    repetition_penalty
    1

    Output

    A large language model is a sophisticated artificial intelligence system that has been trained on an extensive corpus of text data, often covering billions or trillions of words. These models, typically based on deep learning architectures like transformers, are designed to understand and generate human-like language by learning patterns and relationships within the text. They are capable of performing a wide range of natural language processing tasks, such as text generation, language translation, answering questions, and even writing coherent responses to given prompts. Large language models have become increasingly popular in recent years due to their impressive ability to capture context and generate contextually relevant responses. They are often pre-trained on massive datasets and then fine-tuned on specific tasks, allowing them to adapt their knowledge for various applications. However, they also raise concerns about the potential for bias and the need for careful management, as they can potentially produce unintended or inappropriate outputs.
    Generated in

Want to make some of these yourself?

Run this model