# topogpt3: model

topogpt3: model groups 12 files (py) around TopoGPT2Config, __post_init__, setup_logger, set_seed, QuaternionOps. Diagnostico estatico de un checkpoint TopoGPT3 congelado.

```mermaid
graph LR
    eval["eval"]
    root["root"]
    topogpt3["topogpt3"]
    eval -- "calls into" --> topogpt3
    root -- "calls into" --> topogpt3
    topogpt3 -- "calls into" --> eval
    topogpt3 -- "calls into" --> root
```

## eval (2.1)

eval groups 2 files (py) around phase_discretization, synthetic_winding, static_kappa, context_length_diagnostic, main. Diagnostico estatico de un checkpoint TopoGPT3 congelado.

## root (2.2)

root groups 3 files (py) around LLMBackend, generate, name, GroqBackend, __init__. Standalone inference script for TopoExploit.

## topogpt3 (2.3)

topogpt3 groups 7 files (py) around TopoGPT2Config, __post_init__, setup_logger, set_seed, QuaternionOps. Elastic Weight Consolidation (EWC) and Experience Replay for TopoGPT3.

**Files**:

- eval/diag_static.py
- eval/hodge_cm_ablation.py
- infer_exploitgym.py
- synthetic_dataset.py
- topogpt3/ewc.py
- topogpt3/exploitgym_config.py
- topogpt3/exploitgym_loader.py
- topogpt3/hodge_cm.py
- topogpt3/merged_config.py
- topogpt3/model.py
- topogpt3/train.py
- transfer_weights.py