Upload folder using huggingface_hub
Browse files- config.json +125 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.1,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"adaptor_activation_function": "gelu",
|
7 |
+
"adaptor_dropout": 0.1,
|
8 |
+
"adaptor_hidden_size": 512,
|
9 |
+
"adaptor_init_std": 0.02,
|
10 |
+
"adaptor_scaling_factor": 1.0,
|
11 |
+
"adaptor_tuning": false,
|
12 |
+
"add_bias_logits": false,
|
13 |
+
"add_final_layer_norm": true,
|
14 |
+
"additional_source_wait_k": -1,
|
15 |
+
"alibi_encoding": false,
|
16 |
+
"architectures": [
|
17 |
+
"MBartForConditionalGeneration"
|
18 |
+
],
|
19 |
+
"asymmetric_alibi_encoding": false,
|
20 |
+
"attention_dropout": 0.1,
|
21 |
+
"bos_token_id": 0,
|
22 |
+
"bottleneck_mid_fusion_tokens": 4,
|
23 |
+
"classif_dropout": 0.0,
|
24 |
+
"classifier_dropout": 0.0,
|
25 |
+
"d_model": 1024,
|
26 |
+
"decoder_adaptor_tying_config": null,
|
27 |
+
"decoder_attention_heads": 16,
|
28 |
+
"decoder_ffn_dim": 4096,
|
29 |
+
"decoder_layerdrop": 0.0,
|
30 |
+
"decoder_layers": 12,
|
31 |
+
"decoder_start_token_id": 2,
|
32 |
+
"decoder_tying_config": null,
|
33 |
+
"deep_adaptor_tuning": false,
|
34 |
+
"deep_adaptor_tuning_ffn_only": false,
|
35 |
+
"dropout": 0.1,
|
36 |
+
"early_stopping": true,
|
37 |
+
"embed_low_rank_dim": 0,
|
38 |
+
"encoder_adaptor_tying_config": null,
|
39 |
+
"encoder_attention_heads": 16,
|
40 |
+
"encoder_ffn_dim": 4096,
|
41 |
+
"encoder_layerdrop": 0.0,
|
42 |
+
"encoder_layers": 12,
|
43 |
+
"encoder_tying_config": null,
|
44 |
+
"eos_token_id": 2,
|
45 |
+
"expert_ffn_size": 128,
|
46 |
+
"features_embed_dims": null,
|
47 |
+
"features_vocab_sizes": null,
|
48 |
+
"forced_eos_token_id": 2,
|
49 |
+
"gradient_checkpointing": false,
|
50 |
+
"gradient_reversal_for_domain_classifier": false,
|
51 |
+
"hypercomplex": false,
|
52 |
+
"hypercomplex_n": 2,
|
53 |
+
"ia3_adaptors": false,
|
54 |
+
"id2label": {
|
55 |
+
"0": "LABEL_0",
|
56 |
+
"1": "LABEL_1",
|
57 |
+
"2": "LABEL_2"
|
58 |
+
},
|
59 |
+
"init_std": 0.02,
|
60 |
+
"initialization_scheme": "static",
|
61 |
+
"inititialization_scheme": "static",
|
62 |
+
"is_encoder_decoder": true,
|
63 |
+
"label2id": {
|
64 |
+
"LABEL_0": 0,
|
65 |
+
"LABEL_1": 1,
|
66 |
+
"LABEL_2": 2
|
67 |
+
},
|
68 |
+
"layernorm_adaptor_input": false,
|
69 |
+
"layernorm_prompt_projection": false,
|
70 |
+
"lora_adaptor_rank": 2,
|
71 |
+
"lora_adaptors": false,
|
72 |
+
"max_length": 200,
|
73 |
+
"max_position_embeddings": 1024,
|
74 |
+
"mid_fusion_layers": 3,
|
75 |
+
"model_type": "mbart",
|
76 |
+
"moe_adaptors": false,
|
77 |
+
"multi_source": false,
|
78 |
+
"multi_source_method": null,
|
79 |
+
"multilayer_softmaxing": null,
|
80 |
+
"no_embed_norm": false,
|
81 |
+
"no_positional_encoding_decoder": false,
|
82 |
+
"no_positional_encoding_encoder": false,
|
83 |
+
"no_projection_prompt": false,
|
84 |
+
"no_scale_attention_embedding": false,
|
85 |
+
"normalize_before": true,
|
86 |
+
"normalize_embedding": true,
|
87 |
+
"num_beams": 5,
|
88 |
+
"num_domains_for_domain_classifier": -1,
|
89 |
+
"num_experts": 8,
|
90 |
+
"num_hidden_layers": 12,
|
91 |
+
"num_moe_adaptor_experts": 4,
|
92 |
+
"num_prompts": 100,
|
93 |
+
"num_sparsify_blocks": 8,
|
94 |
+
"output_past": true,
|
95 |
+
"pad_token_id": 1,
|
96 |
+
"parallel_adaptors": false,
|
97 |
+
"positional_encodings": false,
|
98 |
+
"postnorm_decoder": false,
|
99 |
+
"postnorm_encoder": false,
|
100 |
+
"prompt_dropout": 0.1,
|
101 |
+
"prompt_init_std": 0.02,
|
102 |
+
"prompt_projection_hidden_size": 4096,
|
103 |
+
"prompt_tuning": false,
|
104 |
+
"recurrent_projections": 1,
|
105 |
+
"residual_connection_adaptor": false,
|
106 |
+
"residual_connection_prompt": false,
|
107 |
+
"rope_encoding": false,
|
108 |
+
"scale_embedding": true,
|
109 |
+
"softmax_bias_tuning": false,
|
110 |
+
"softmax_temperature": 1.0,
|
111 |
+
"sparsification_temperature": 3.0,
|
112 |
+
"sparsify_attention": false,
|
113 |
+
"sparsify_ffn": false,
|
114 |
+
"static_position_embeddings": false,
|
115 |
+
"target_vocab_size": 0,
|
116 |
+
"temperature_calibration": false,
|
117 |
+
"tokenizer_class": "MBart50Tokenizer",
|
118 |
+
"transformers_version": "4.3.2",
|
119 |
+
"unidirectional_encoder": false,
|
120 |
+
"use_cache": true,
|
121 |
+
"use_moe": false,
|
122 |
+
"use_tanh_activation_prompt": false,
|
123 |
+
"vocab_size": 250054,
|
124 |
+
"wait_k": -1
|
125 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:154c3030e1c4eb37fbcbba33b9c9afb4880c2d07eefa1039cddd11b9e0e1cd39
|
3 |
+
size 2444725607
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"src_lang": null, "tgt_lang": null, "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "bos_token": "<s>", "tokenizer_file": null, "language_codes": "ML50", "special_tokens_map_file": "/home/suraj/projects/mbart-50/mbart-50/special_tokens_map.json", "name_or_path": "facebook/mbart-large-50-many-to-many-mmt", "use_fast": false}
|