Hugging Face's logo

shivash
/
testingmodel

PyTorch
enhanced_hybrid_transformer
Model card Files
xet
Community
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Enhanced Hybrid Transformer 416M

🚀 416,417,792 parameter transformer with modern optimizations.

Features

  • 24 layers × 16 heads
  • GQA-4 (Grouped Query Attention)
  • SwiGLU activation
  • RMSNorm normalization
  • RoPE positional embeddings

Contents

  • pytorch_model.bin - Model weights
  • config.json - Model configuration
  • tokenizer.json - Tokenizer files
  • README.md - This file

Usage

Load with the original repository code for full functionality.

🚀 Generated with Claude Code

Downloads last month
9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support