Official

ibm-granite / granite-3.2-8b-instruct

  • Public
  • 334.5K runs
  • Priced per token
  • License
Run with an API

New model available: Try out Granite-3.3-8b-instruct View the new model

Playground API Examples Train Beta README

  • Prediction

    ibm-granite/granite-3.2-8b-instruct
    Official model
    ID
    7kqz6aczz5rme0cns1rrsj94yr
    Status
    Succeeded
    Source
    Web
    Total duration
    Created

    Input

    top_p
    0.9
    prompt
    How is perplexity measured for LLMs and why is it useful?
    max_tokens
    512
    min_tokens
    0
    temperature
    0.6
    system_prompt
    You are a helpful assistant.
    presence_penalty
    0
    frequency_penalty
    0

    Output

    Perplexity is a common metric used to evaluate the performance of language models, including large language models (LLMs). It's a measure of how well a model predicts a sample. Perplexity is calculated based on the concept of cross-entropy. In simpler terms, it's a way to measure how surprised the model is by the test data. The lower the perplexity, the less surprised the model is, and the better it predicts the data. Here's a simple breakdown of how it's calculated: 1. The model is given a test set of sentences. 2. For each word in the sentence, the model calculates the probability of that word given all the previous words. 3. The perplexity is then the inverse probability of the entire sentence, averaged over the whole test set. The formula for perplexity (PP) is: PP(W) = exp(-1/N * Σ log P(wi|w1...wi-1)) Where: - W is the test set of sentences, - N is the number of words in the test set, - wi is each word in the test set, - P(wi|w1...wi-1) is the probability assigned by the model to word wi given the previous words. Perplexity is useful for several reasons: 1. **Model Comparison**: It provides a standard way to compare different models. A lower perplexity score generally indicates a better model. 2. **Model Improvement**: It helps in identifying areas where the model is struggling. If a certain type of sentence or vocabulary consistently results in high perplexity, it indicates a weakness in the model that can be addressed through further training or adjustments. 3. **Understanding Model Behavior**: It gives insights into how the model understands language. A lower perplexity suggests the model has a better grasp of the language's structure and usage. 4. **Evaluation of Unseen Data**: While it's trained on a specific corpus, perplexity can be calculated on unseen data to evaluate the model's generalization capability. However, it's important to note that while perplexity is a widely used metric, it's not without its limitations. For instance, it doesn't directly correlate with human judgment of fluency or coherence, and
    Generated in
    Input tokens
    22
    Output tokens
    510
    Tokens per second
    140.55 tokens / second
    Time to first token
    Tweak itShareReport

Want to make some of these yourself?

Run this model