| { |
| "architecture": { |
| "attention_variant": "MHA", |
| "family": "masked_lm", |
| "is_moe": false, |
| "positional": "rope", |
| "tie_word_embeddings": true, |
| "view": "encoder" |
| }, |
| "capabilities": { |
| "attention_backends": [ |
| "eager" |
| ], |
| "attention_patterns": [ |
| "bidirectional" |
| ], |
| "attention_schedule": null, |
| "task_heads": [ |
| "masked_lm", |
| "sequence_classification", |
| "token_classification" |
| ], |
| "tensor_parallel": false |
| }, |
| "components": [], |
| "config": { |
| "class_name": "EsmConfig", |
| "model_type": "esm", |
| "module": "transformers.models.esm.configuration_esm", |
| "referenced_fields": {}, |
| "salient_fields": { |
| "hidden_size": 768, |
| "intermediate_size": 3072, |
| "is_encoder_decoder": false, |
| "max_position_embeddings": 1026, |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "tie_word_embeddings": true |
| } |
| }, |
| "edges": [], |
| "extends": null, |
| "model_type": "esm", |
| "provenance": { |
| "config_class": "EsmConfig", |
| "config_module": "transformers.models.esm.configuration_esm", |
| "model_class": null, |
| "model_module": null |
| }, |
| "repeats": [], |
| "schema_version": "architecture-template-v0", |
| "status": "config_only", |
| "templates": [], |
| "warnings": [ |
| "meta build failed (TypeError): empty() received an invalid combination of arguments - got (tuple, dtype=NoneType, device=NoneType), but expected one of:\n * (tuple of ints size, *, tuple of names names, torch.memory_format memory_fo" |
| ] |
| } |
|
|
