File size: 3,969 Bytes
5161b97 1408553 5161b97 1408553 5161b97 1408553 5161b97 1408553 5161b97 1408553 5161b97 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 |
{
"_name_or_path": "ayjays132/CustomGPT2Conversational",
"activation_function": "gelu_new",
"advanced_model_options": {
"contextual_embeddings": {
"approaches": [
"contextual_attention_mechanisms",
"semantic_embedding_regularization"
],
"enable": true
},
"dynamic_adaptation": {
"enable": true,
"techniques": [
"adaptive_layer_dropping",
"dynamic_context_window"
]
},
"innovative_neuron_growth": {
"enable": true,
"strategies": [
"selective_neuron_pruning",
"progressive_neuron_expansion"
]
},
"memory_optimization": {
"enable": true,
"methods": [
"gradient_checkpointing",
"memory-efficient_attention"
]
},
"meta_learning": {
"approaches": [
"meta_learning_rate_adjustment",
"online_adaptation"
],
"enable": true
},
"secret_advanced_options": {
"adaptive_token_embedding": {
"enable": true,
"strategies": [
"dynamic_embedding_resizing",
"contextual_embedding_scaling"
]
},
"future_context_prediction": {
"enable": true,
"techniques": [
"lookahead_context_integration",
"predictive_attention_mechanisms"
]
},
"multi_modal_integration": {
"enable": true,
"methods": [
"text_image_alignment",
"cross_modal_attention"
]
}
}
},
"activation_dropout": 0.1,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"BartModel"
],
"attention_dropout": 0.1,
"bos_token_id": 0,
"classif_dropout": 0.1,
"classifier_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 2,
"dropout": 0.1,
"early_stopping": true,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 2,
"forced_eos_token_id": 2,
"forced_bos_token_id": 0,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"max_position_embeddings": 1024,
"model_type": "bart",
"n_ctx": 1024,
"n_embd": 1024,
"n_head": 16,
"n_inner": null,
"n_layer": 24,
"n_positions": 1024,
"no_repeat_ngram_size": 2,
"num_beams": 5,
"num_embeddings": 50257,
"num_heads": 64,
"num_layers": 24,
"output_attentions": true,
"output_hidden_states": true,
"pad_token_id": 50267,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"sep_token_id": 50267,
"special_tokens": {
"additional_special_tokens": [
"<greeting>",
"<farewell>",
"<thank>",
"<apology>"
],
"bos_token": "<bos>",
"cls_token": "<cls>",
"eos_token": "<eos>",
"mask_token": "<mask>",
"pad_token": "<pad>",
"sep_token": "<sep>",
"unk_token": "<unk>"
},
"state_shape": null,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"target_q_model": null,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"early_stopping": true,
"length_penalty": 1.0,
"max_length": 2048,
"min_length": 64,
"no_repeat_ngram_size": 2,
"num_beams": 8,
"num_return_sequences": 3,
"repetition_penalty": 1.2,
"temperature": 0.9,
"top_k": 50,
"top_p": 0.95
}
},
"torch_dtype": "float32",
"transformers_version": "4.44.0",
"use_cache": true,
"vocab_size": 50257
} |