| { | |
| "architectures": [ | |
| "EncoderDecoderModel" | |
| ], | |
| "cache_dir": "./cache", | |
| "decoder": { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "openai-community/gpt2-large", | |
| "activation_function": "gelu_new", | |
| "add_cross_attention": true, | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "initializer_range": 0.02, | |
| "is_decoder": true, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "n_embd": 1280, | |
| "n_head": 20, | |
| "n_inner": null, | |
| "n_layer": 36, | |
| "n_positions": 1024, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 50 | |
| } | |
| }, | |
| "torch_dtype": "float32", | |
| "use_cache": true, | |
| "vocab_size": 50257 | |
| }, | |
| "decoder_start_token_id": 50256, | |
| "encoder": { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "Shuu12121/CodeModernBERT-Ghost", | |
| "architectures": [ | |
| "ModernBertForMaskedLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 50000, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.0, | |
| "classifier_pooling": "cls", | |
| "cls_token_id": 50281, | |
| "decoder_bias": true, | |
| "deterministic_flash_attn": false, | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 50001, | |
| "global_attn_every_n_layers": 3, | |
| "global_rope_theta": 160000.0, | |
| "hidden_activation": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "local_attention": 128, | |
| "local_attention_rope_theta": 10000, | |
| "local_attention_window": 128, | |
| "local_rope_theta": 10000.0, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "model_type": "modernbert", | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "repad_logits_with_grad": false, | |
| "rope_theta": 160000, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "torch_dtype": "float32", | |
| "type_vocab_size": 2, | |
| "vocab_size": 50004 | |
| }, | |
| "eos_token_id": 50256, | |
| "is_encoder_decoder": true, | |
| "model_type": "encoder-decoder", | |
| "pad_token_id": 50256, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.51.1" | |
| } | |