Skip to main content

Small Base Model

The Small Base model is the smallest model available. It is designed for lightweight tasks and optimized for mobile and edge deployment.

M
Written by Michael McCarty
Updated over 2 months ago

The Small Base model is the smallest language model available on Minibase. It is designed for lightweight tasks and optimized for mobile and edge deployment. While it does not provide deep reasoning or long, dynamic conversations, it performs well on simple, repeatable tasks where responses are short and predictable.

Typical use cases include:

  • Classification: labeling text or short inputs with predefined categories.

  • Extraction: pulling out keywords or structured values from text.

  • Simple Q&A: answering direct factual questions with short responses.

  • Instruction Following (basic): handling narrow, repeatable tasks reliably.

This model is best when efficiency and small memory footprint are more important than conversational depth or creativity.

Model Specs

  • # of Parameters: ~135M

  • Format Type: causal_lm

  • Download Size: ~135 MB (estimate)

  • Max Sequence Length: 1,024 tokens

  • Context Window: 1,024 tokens

The compact size makes it fast and efficient, ideal for edge devices and resource-limited environments.

How to Use

Step 1: Choose the model

  • From the Models tab, select the Small Base model when creating a new fine-tuned model.

Step 2: Prepare your dataset

  • Use Instruction, Input, and Response fields, keeping examples short and consistent.

  • Example:

    • Instruction: “Classify sentiment as Positive or Negative”

    • Input: “I love this product!”

    • Response: “Positive”

Step 3: Train your model

  • Upload in Excel, JSON, or JSON-L format. All files are standardized to JSON-L.

  • Start fine-tuning; training uses LoRA for efficient adaptation.

Step 4: Test in the browser

  • On the Model Details page, you can chat with your model directly.

  • Adjust Temperature (randomness) and Max Tokens (length) to evaluate its behavior.

Step 5: Deploy or download

  • Download in GGUF format for local or mobile use.

  • Or deploy instantly with Minibase Cloud to access it via APIs.

Tips & Best Practices

  1. Keep tasks narrow: This model works best when it only has to do one specific job repeatedly.

  2. Use small, clean datasets: Consistency matters more than size for micro tasks.

    1. Ideally, datasets will include between 10,000 to 50,000 examples.

  3. Short outputs are ideal: Design tasks around labels, keywords, or short responses rather than long-form text.

  4. Quantization options:

    1. High (Q8_0): best quality, near-lossless.

    2. Medium (Q4_K_M): balanced, recommended for most users.

    3. Low (Q4_K_S): smallest, fastest, optimized for mobile/edge.

Troubleshooting

Responses are inconsistent

Ensure training examples are uniform and tightly scoped. Variability can confuse smaller models.

The model doesn’t give long answers

The Small Base model isn’t designed for that. Fix: Use the Standard or Large Base model better suited for more complex output.

Training still feels slow

While smaller models train faster, dataset size matters. Try a smaller dataset for testing, then scale up once satisfied with the model's performance.

Need More Help?

Need More Help?
Join our Discord support server to chat with our team and get real-time assistance.

Did this answer your question?