Upload MBartForConditionalGeneration
Browse files- config.json +81 -0
- generation_config.json +10 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "lmqg_output/trimmed_qg/mbart-large-cc25-trimmed-ru-ruquad-qg/best_model",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": true,
|
| 8 |
+
"add_prefix": false,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"MBartForConditionalGeneration"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"bos_token_id": 0,
|
| 14 |
+
"classif_dropout": 0.0,
|
| 15 |
+
"classifier_dropout": 0.0,
|
| 16 |
+
"d_model": 1024,
|
| 17 |
+
"decoder_attention_heads": 16,
|
| 18 |
+
"decoder_ffn_dim": 4096,
|
| 19 |
+
"decoder_layerdrop": 0.0,
|
| 20 |
+
"decoder_layers": 12,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"encoder_attention_heads": 16,
|
| 23 |
+
"encoder_ffn_dim": 4096,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 12,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"id2label": {
|
| 29 |
+
"0": "LABEL_0",
|
| 30 |
+
"1": "LABEL_1",
|
| 31 |
+
"2": "LABEL_2"
|
| 32 |
+
},
|
| 33 |
+
"init_std": 0.02,
|
| 34 |
+
"is_encoder_decoder": true,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"LABEL_0": 0,
|
| 37 |
+
"LABEL_1": 1,
|
| 38 |
+
"LABEL_2": 2
|
| 39 |
+
},
|
| 40 |
+
"max_length": 1024,
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "mbart",
|
| 43 |
+
"normalize_before": true,
|
| 44 |
+
"normalize_embedding": true,
|
| 45 |
+
"num_beams": 5,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"output_past": true,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": true,
|
| 50 |
+
"static_position_embeddings": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"translation_en_to_ro": {
|
| 53 |
+
"decoder_start_token_id": 250020
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.26.1",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 99662,
|
| 60 |
+
"vocabtrimmer": {
|
| 61 |
+
"mining_config": {
|
| 62 |
+
"dataset": "vocabtrimmer/mc4_validation",
|
| 63 |
+
"dataset_column": "text",
|
| 64 |
+
"dataset_name": "ru",
|
| 65 |
+
"dataset_split": "validation",
|
| 66 |
+
"language": "ru",
|
| 67 |
+
"min_frequency": 2,
|
| 68 |
+
"target_vocab_size": null
|
| 69 |
+
},
|
| 70 |
+
"stats": {
|
| 71 |
+
"compression_rate_embedding": 39.86009510972815,
|
| 72 |
+
"compression_rate_full": 74.79343207020544,
|
| 73 |
+
"parameter_size_embedding/raw": 512055296,
|
| 74 |
+
"parameter_size_embedding/trimmed": 204105728,
|
| 75 |
+
"parameter_size_full/raw": 610851840,
|
| 76 |
+
"parameter_size_full/trimmed": 456877056,
|
| 77 |
+
"vocab_size/raw": 250027,
|
| 78 |
+
"vocab_size/trimmed": 99661
|
| 79 |
+
}
|
| 80 |
+
}
|
| 81 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"forced_eos_token_id": 2,
|
| 6 |
+
"max_length": 1024,
|
| 7 |
+
"num_beams": 5,
|
| 8 |
+
"pad_token_id": 1,
|
| 9 |
+
"transformers_version": "4.26.1"
|
| 10 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73720df29aa743898c5f721eb87aa110314a43726a1d77a94ee7a03873bb578a
|
| 3 |
+
size 1828086813
|