File size: 8,110 Bytes
18ec7db 7c3ba9d 18ec7db 305743f 18ec7db 80e26aa 18ec7db |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 |
{
"_name_or_path": "Shivam098/opt-translation",
"_num_labels": 3,
"activation_dropout": 0.0,
"activation_function": "relu",
"add_bias_logits": false,
"add_final_layer_norm": true,
"architectures": [
"MBartForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"classif_dropout": 0.0,
"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,
"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_length": 200,
"max_position_embeddings": 1024,
"model_type": "mbart",
"normalize_before": true,
"normalize_embedding": true,
"num_beams": 5,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"quantization_config": {
"batch_size": 1,
"bits": 4,
"block_name_to_quantize": "model.decoder.layers",
"damp_percent": 0.1,
"dataset": "c4",
"desc_act": false,
"disable_exllama": true,
"group_size": 128,
"model_seqlen": 1024,
"module_name_preceding_first_block": [
"model.shared",
"model.encoder.embed_tokens",
"model.encoder.embed_positions",
"model.encoder.layers.0.self_attn.k_proj",
"model.encoder.layers.0.self_attn.v_proj",
"model.encoder.layers.0.self_attn.q_proj",
"model.encoder.layers.0.self_attn.out_proj",
"model.encoder.layers.0.self_attn",
"model.encoder.layers.0.self_attn_layer_norm",
"model.encoder.layers.0.activation_fn",
"model.encoder.layers.0.fc1",
"model.encoder.layers.0.fc2",
"model.encoder.layers.0.final_layer_norm",
"model.encoder.layers.0",
"model.encoder.layers.1.self_attn.k_proj",
"model.encoder.layers.1.self_attn.v_proj",
"model.encoder.layers.1.self_attn.q_proj",
"model.encoder.layers.1.self_attn.out_proj",
"model.encoder.layers.1.self_attn",
"model.encoder.layers.1.self_attn_layer_norm",
"model.encoder.layers.1.activation_fn",
"model.encoder.layers.1.fc1",
"model.encoder.layers.1.fc2",
"model.encoder.layers.1.final_layer_norm",
"model.encoder.layers.1",
"model.encoder.layers.2.self_attn.k_proj",
"model.encoder.layers.2.self_attn.v_proj",
"model.encoder.layers.2.self_attn.q_proj",
"model.encoder.layers.2.self_attn.out_proj",
"model.encoder.layers.2.self_attn",
"model.encoder.layers.2.self_attn_layer_norm",
"model.encoder.layers.2.activation_fn",
"model.encoder.layers.2.fc1",
"model.encoder.layers.2.fc2",
"model.encoder.layers.2.final_layer_norm",
"model.encoder.layers.2",
"model.encoder.layers.3.self_attn.k_proj",
"model.encoder.layers.3.self_attn.v_proj",
"model.encoder.layers.3.self_attn.q_proj",
"model.encoder.layers.3.self_attn.out_proj",
"model.encoder.layers.3.self_attn",
"model.encoder.layers.3.self_attn_layer_norm",
"model.encoder.layers.3.activation_fn",
"model.encoder.layers.3.fc1",
"model.encoder.layers.3.fc2",
"model.encoder.layers.3.final_layer_norm",
"model.encoder.layers.3",
"model.encoder.layers.4.self_attn.k_proj",
"model.encoder.layers.4.self_attn.v_proj",
"model.encoder.layers.4.self_attn.q_proj",
"model.encoder.layers.4.self_attn.out_proj",
"model.encoder.layers.4.self_attn",
"model.encoder.layers.4.self_attn_layer_norm",
"model.encoder.layers.4.activation_fn",
"model.encoder.layers.4.fc1",
"model.encoder.layers.4.fc2",
"model.encoder.layers.4.final_layer_norm",
"model.encoder.layers.4",
"model.encoder.layers.5.self_attn.k_proj",
"model.encoder.layers.5.self_attn.v_proj",
"model.encoder.layers.5.self_attn.q_proj",
"model.encoder.layers.5.self_attn.out_proj",
"model.encoder.layers.5.self_attn",
"model.encoder.layers.5.self_attn_layer_norm",
"model.encoder.layers.5.activation_fn",
"model.encoder.layers.5.fc1",
"model.encoder.layers.5.fc2",
"model.encoder.layers.5.final_layer_norm",
"model.encoder.layers.5",
"model.encoder.layers.6.self_attn.k_proj",
"model.encoder.layers.6.self_attn.v_proj",
"model.encoder.layers.6.self_attn.q_proj",
"model.encoder.layers.6.self_attn.out_proj",
"model.encoder.layers.6.self_attn",
"model.encoder.layers.6.self_attn_layer_norm",
"model.encoder.layers.6.activation_fn",
"model.encoder.layers.6.fc1",
"model.encoder.layers.6.fc2",
"model.encoder.layers.6.final_layer_norm",
"model.encoder.layers.6",
"model.encoder.layers.7.self_attn.k_proj",
"model.encoder.layers.7.self_attn.v_proj",
"model.encoder.layers.7.self_attn.q_proj",
"model.encoder.layers.7.self_attn.out_proj",
"model.encoder.layers.7.self_attn",
"model.encoder.layers.7.self_attn_layer_norm",
"model.encoder.layers.7.activation_fn",
"model.encoder.layers.7.fc1",
"model.encoder.layers.7.fc2",
"model.encoder.layers.7.final_layer_norm",
"model.encoder.layers.7",
"model.encoder.layers.8.self_attn.k_proj",
"model.encoder.layers.8.self_attn.v_proj",
"model.encoder.layers.8.self_attn.q_proj",
"model.encoder.layers.8.self_attn.out_proj",
"model.encoder.layers.8.self_attn",
"model.encoder.layers.8.self_attn_layer_norm",
"model.encoder.layers.8.activation_fn",
"model.encoder.layers.8.fc1",
"model.encoder.layers.8.fc2",
"model.encoder.layers.8.final_layer_norm",
"model.encoder.layers.8",
"model.encoder.layers.9.self_attn.k_proj",
"model.encoder.layers.9.self_attn.v_proj",
"model.encoder.layers.9.self_attn.q_proj",
"model.encoder.layers.9.self_attn.out_proj",
"model.encoder.layers.9.self_attn",
"model.encoder.layers.9.self_attn_layer_norm",
"model.encoder.layers.9.activation_fn",
"model.encoder.layers.9.fc1",
"model.encoder.layers.9.fc2",
"model.encoder.layers.9.final_layer_norm",
"model.encoder.layers.9",
"model.encoder.layers.10.self_attn.k_proj",
"model.encoder.layers.10.self_attn.v_proj",
"model.encoder.layers.10.self_attn.q_proj",
"model.encoder.layers.10.self_attn.out_proj",
"model.encoder.layers.10.self_attn",
"model.encoder.layers.10.self_attn_layer_norm",
"model.encoder.layers.10.activation_fn",
"model.encoder.layers.10.fc1",
"model.encoder.layers.10.fc2",
"model.encoder.layers.10.final_layer_norm",
"model.encoder.layers.10",
"model.encoder.layers.11.self_attn.k_proj",
"model.encoder.layers.11.self_attn.v_proj",
"model.encoder.layers.11.self_attn.q_proj",
"model.encoder.layers.11.self_attn.out_proj",
"model.encoder.layers.11.self_attn",
"model.encoder.layers.11.self_attn_layer_norm",
"model.encoder.layers.11.activation_fn",
"model.encoder.layers.11.fc1",
"model.encoder.layers.11.fc2",
"model.encoder.layers.11.final_layer_norm",
"model.encoder.layers.11",
"model.encoder.layers",
"model.encoder.layernorm_embedding",
"model.encoder.layer_norm",
"model.encoder",
"model.decoder.embed_tokens",
"model.decoder.embed_positions"
],
"pad_token_id": null,
"quant_method": "gptq",
"sym": true,
"tokenizer": null,
"true_sequential": true,
"use_cuda_fp16": true
},
"scale_embedding": true,
"static_position_embeddings": false,
"tokenizer_class": "MBart50Tokenizer",
"torch_dtype": "float16",
"transformers_version": "4.33.0.dev0",
"use_cache": true,
"vocab_size": 250054
}
|