model_310248297_tiny_transformer_small.py

Model Overview

A small-scale implementation of the tiny transformer architecture, built for retrieval tasks.

Architecture

• Architecture: tiny transformer
• Scale: small
• Attention: grouped query
• Fusion strategy: concat mlp
• Task head: retrieval
• Activation: approx gelu
• Normalization: layernorm
• Initialization: trunc normal

Training

• Optimizer: adam
• LR scheduler: step

Files

• model_310248297_tiny_transformer_small.py — main artifact of this repository

License

See the license field above.