agentsclimarketplace
Sign in

Setfit few shot

Skill a5c-ai/babysitter/library/specializations/ai-agents-conversational/skills/setfit-few-shot

SetFit few-shot learning for efficient intent classification with minimal dataFrom its SKILL.md

Install
npx -y skills add a5c-ai/babysitter --skill setfit-few-shot

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.5 KB, 217 tokens by cl100k_base, as published. Nobody here has run it

SetFit Few-Shot Skill

Capabilities

  • Train SetFit models with few examples per class
  • Configure contrastive learning settings
  • Implement efficient classification pipelines
  • Design few-shot training strategies
  • Set up model evaluation
  • Deploy lightweight classifiers

Target Processes

  • intent-classification-system

Implementation Details

SetFit Advantages

  1. Few Examples: 8-16 examples per class
  2. No Prompts: No prompt engineering needed
  3. Fast Training: Minutes vs hours
  4. Small Models: Sentence transformer base

Training Process

  • Contrastive fine-tuning of embeddings
  • Classification head training
  • Iterative sampling strategies

Configuration Options

  • Base sentence transformer model
  • Number of training examples
  • Contrastive learning epochs
  • Classification head architecture
  • Evaluation metrics

Best Practices

  • Diverse few-shot examples
  • Balance class examples
  • Use appropriate base model
  • Validate on held-out data

Dependencies

  • setfit
  • sentence-transformers

What ships with it: 1 file

480 B alongside SKILL.md

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.