OpenParable
Skip to content
← Back to skills

Huggingface Classifier

Development
huggingface-classifier

Huggingface Classifier is an Agent Skill for development published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Hugging Face transformer model fine-tuning and inference for intent classification

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/ai-agents-conversational/skills/huggingface-classifier/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/huggingface-classifier, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

HuggingFace Classifier Skill

Capabilities

  • Fine-tune transformer models for classification
  • Configure training pipelines with Trainer API
  • Implement inference with optimizations
  • Design label schemas and mappings
  • Set up model evaluation and metrics
  • Deploy models with HF Inference API

Target Processes

  • intent-classification-system
  • entity-extraction-slot-filling

Implementation Details

Model Types

  1. BERT-based: bert-base-uncased, distilbert
  2. RoBERTa-based: roberta-base, xlm-roberta
  3. DeBERTa: deberta-v3-base
  4. Domain-specific: FinBERT, BioBERT

Training Configuration

  • Dataset preparation
  • Tokenization settings
  • Training arguments
  • Evaluation metrics
  • Early stopping

Configuration Options

  • Model selection
  • Number of labels
  • Training hyperparameters
  • Batch sizes
  • Learning rate schedules

Best Practices

  • Use appropriate base model
  • Proper train/val/test splits
  • Monitor for overfitting
  • Evaluate on representative data

Dependencies

  • transformers
  • datasets
  • accelerate