nl2sql-pretrained / model_info.json
karthik-2905's picture
Upload folder using huggingface_hub
e18f039 verified
{
"model_name": "MySQL Query Generator - From Scratch",
"version": "1.0.0",
"description": "GPT-style transformer trained completely from scratch for MySQL query generation",
"architecture": {
"type": "GPT-style Transformer (Decoder-only)",
"layers": 8,
"attention_heads": 8,
"hidden_size": 512,
"feedforward_size": 2048,
"max_sequence_length": 512,
"dropout": 0.1
},
"training": {
"type": "from_scratch_pretraining",
"no_pretrained_weights": true,
"epochs": 8,
"training_time_minutes": 12,
"hardware": "RTX 5080 16GB",
"framework": "PyTorch",
"optimizer": "AdamW",
"scheduler": "CosineAnnealingLR"
},
"performance": {
"final_validation_loss": 0.3485,
"final_training_loss": 0.3178,
"final_perplexity": 1.42,
"convergence": "excellent",
"overfitting": "none_detected",
"quality": "production_ready"
},
"model_stats": {
"total_parameters": 29789184,
"vocabulary_size": 4206,
"training_examples": 24293,
"model_size_mb": 113.63671875
},
"dataset": {
"size": 24293,
"sources": [
"synthetic_sql",
"spider_dataset",
"wikisql_dataset"
],
"diversity": "high",
"mysql_specific": true
},
"license": "Open Source",
"created_date": "2025-07-18T10:20:16.546994",
"authors": "Anonymous",
"contact": "Open source community"
}