| { | |
| "model_type": "biotitan", | |
| "architecture": "titans", | |
| "n_genes": 25424, | |
| "d_model": 256, | |
| "n_layers": 6, | |
| "n_heads": 4, | |
| "d_ff": 512, | |
| "max_seq_len": 2048, | |
| "memory_depth": 2, | |
| "n_persistent": 32, | |
| "dropout": 0.02, | |
| "vocab_size": 25426, | |
| "pad_token_id": 0, | |
| "mask_token_id": 25425, | |
| "training": { | |
| "dataset": "tabula_sapiens", | |
| "n_cells": 254394, | |
| "epochs": 2, | |
| "batch_size": 32, | |
| "learning_rate": 5e-4, | |
| "weight_decay": 0.001, | |
| "warmup_steps": 300, | |
| "mask_prob": 0.15, | |
| "optimizer": "AdamW", | |
| "mixed_precision": true | |
| }, | |
| "files": { | |
| "model_weights": "biotitan-20m-tabula-sapiens.pt", | |
| "token_dictionary": "token_dictionary.pkl", | |
| "contextualized_embeddings": "gene_embeddings_ctx_254k.parquet", | |
| "static_embeddings": "gene_embeddings_static.parquet" | |
| }, | |
| "benchmark_results": { | |
| "overall_53_tasks": { | |
| "static_auc": 0.636, | |
| "ctx_254k_auc": 0.716, | |
| "geneformer_v1_auc": 0.782 | |
| }, | |
| "family_averages": { | |
| "expression_23_tasks": { "static": 0.732, "ctx_254k": 0.815, "geneformer": 0.869 }, | |
| "genomic_properties_7_tasks": { "static": 0.640, "ctx_254k": 0.687, "geneformer": 0.782 }, | |
| "regulatory_functions_4_tasks": { "static": 0.623, "ctx_254k": 0.704, "geneformer": 0.759 }, | |
| "localization_2_tasks": { "static": 0.616, "ctx_254k": 0.699, "geneformer": 0.725 }, | |
| "protein_properties_17_tasks": { "static": 0.571, "ctx_254k": 0.598, "geneformer": 0.678 } | |
| } | |
| } | |
| } | |