(config_class, model)
| 69 | |
| 70 | |
| 71 | def set_optimizer_flags(config_class, model): |
| 72 | if config_class.optimizer_name == MUON_OPTIMIZER: |
| 73 | for name, p in model.named_parameters(): |
| 74 | if p.ndim >= 2 and not any(keyword in name.lower() for keyword in ("embed", "lm_head")): |
| 75 | setattr(p, "use_muon", True) |
| 76 | else: |
| 77 | setattr(p, "use_muon", False) |
| 78 | |
| 79 | |
| 80 | def initialize(args=None, |
no outgoing calls
no test coverage detected
searching dependent graphs…