Shuu12121/CodeEncoderDecoderModel-Ghost-large
027
1{2 "architectures": [3 "EncoderDecoderModel"4 ],5 "cache_dir": "./cache",6 "decoder": {7 "_attn_implementation_autoset": true,8 "_name_or_path": "openai-community/gpt2-large",9 "activation_function": "gelu_new",10 "add_cross_attention": true,11 "architectures": [12 "GPT2LMHeadModel"13 ],14 "attn_pdrop": 0.1,15 "embd_pdrop": 0.1,16 "initializer_range": 0.02,17 "is_decoder": true,18 "layer_norm_epsilon": 1e-05,19 "model_type": "gpt2",20 "n_ctx": 1024,21 "n_embd": 1280,22 "n_head": 20,23 "n_inner": null,24 "n_layer": 36,25 "n_positions": 1024,26 "reorder_and_upcast_attn": false,27 "resid_pdrop": 0.1,28 "scale_attn_by_inverse_layer_idx": false,29 "scale_attn_weights": true,30 "summary_activation": null,31 "summary_first_dropout": 0.1,32 "summary_proj_to_labels": true,33 "summary_type": "cls_index",34 "summary_use_proj": true,35 "task_specific_params": {36 "text-generation": {37 "do_sample": true,38 "max_length": 5039 }40 },41 "torch_dtype": "float32",42 "use_cache": true,43 "vocab_size": 5025744 },45 "decoder_start_token_id": 50256,46 "encoder": {47 "_attn_implementation_autoset": true,48 "_name_or_path": "Shuu12121/CodeModernBERT-Ghost",49 "architectures": [50 "ModernBertForMaskedLM"51 ],52 "attention_bias": false,53 "attention_dropout": 0.0,54 "attention_probs_dropout_prob": 0.1,55 "bos_token_id": 50000,56 "classifier_activation": "gelu",57 "classifier_bias": false,58 "classifier_dropout": 0.0,59 "classifier_pooling": "cls",60 "cls_token_id": 50281,61 "decoder_bias": true,62 "deterministic_flash_attn": false,63 "embedding_dropout": 0.0,64 "eos_token_id": 50001,65 "global_attn_every_n_layers": 3,66 "global_rope_theta": 160000.0,67 "hidden_activation": "gelu",68 "hidden_dropout_prob": 0.1,69 "hidden_size": 768,70 "initializer_cutoff_factor": 2.0,71 "initializer_range": 0.02,72 "intermediate_size": 3072,73 "local_attention": 128,74 "local_attention_rope_theta": 10000,75 "local_attention_window": 128,76 "local_rope_theta": 10000.0,77 "max_position_embeddings": 2048,78 "mlp_bias": false,79 "mlp_dropout": 0.0,80 "model_type": "modernbert",81 "norm_bias": false,82 "norm_eps": 1e-05,83 "num_attention_heads": 12,84 "num_hidden_layers": 12,85 "pad_token_id": 0,86 "repad_logits_with_grad": false,87 "rope_theta": 160000,88 "sparse_pred_ignore_index": -100,89 "sparse_prediction": false,90 "torch_dtype": "float32",91 "type_vocab_size": 2,92 "vocab_size": 5000493 },94 "eos_token_id": 50256,95 "is_encoder_decoder": true,96 "model_type": "encoder-decoder",97 "pad_token_id": 50256,98 "torch_dtype": "float32",99 "transformers_version": "4.51.1"100}101 