Upload folder using huggingface_hub
Browse files- added_tokens.json +1 -0
- config.json +100 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 64000, "</s>": 64001, "<2acf>": 64002, "<2eng>": 64003, "<2fra>": 64004, "<2aoa>": 64005, "<2bah>": 64006, "<2brc>": 64007, "<2bzj>": 64008, "<2bzk>": 64009, "<2cab>": 64010, "<2cri>": 64011, "<2crs>": 64012, "<2dcr>": 64013, "<2djk>": 64014, "<2ara>": 64015, "<2ceb>": 64016, "<2deu>": 64017, "<2nep>": 64018, "<2zho>": 64019, "<2fab>": 64020, "<2fng>": 64021, "<2fpe>": 64022, "<2gcf>": 64023, "<2gcr>": 64024, "<2gpe>": 64025, "<2gul>": 64026, "<2gyn>": 64027, "<2hat>": 64028, "<2aze>": 64029, "<2icr>": 64030, "<2jam>": 64031, "<2kea>": 64032, "<2spa>": 64033, "<2kri>": 64034, "<2ktu>": 64035, "<2lou>": 64036, "<2mart1259>": 64037, "<2mfe>": 64038, "<2mue>": 64039, "<2pap>": 64040, "<2por>": 64041, "<2pcm>": 64042, "<2pov>": 64043, "<2pre>": 64044, "<2rcf>": 64045, "<2sag>": 64046, "<2srm>": 64047, "<2srn>": 64048, "<2svc>": 64049, "<2tpi>": 64050, "<2trf>": 64051, "<2wes>": 64052}
|
config.json
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.1,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"adaptor_activation_function": "gelu",
|
5 |
+
"adaptor_dropout": 0.1,
|
6 |
+
"adaptor_hidden_size": 512,
|
7 |
+
"adaptor_init_std": 0.02,
|
8 |
+
"adaptor_scaling_factor": 1.0,
|
9 |
+
"adaptor_tuning": false,
|
10 |
+
"additional_source_wait_k": -1,
|
11 |
+
"alibi_encoding": false,
|
12 |
+
"architectures": [
|
13 |
+
"MBartForConditionalGeneration"
|
14 |
+
],
|
15 |
+
"asymmetric_alibi_encoding": false,
|
16 |
+
"attention_dropout": 0.1,
|
17 |
+
"bos_token_id": 64000,
|
18 |
+
"bottleneck_mid_fusion_tokens": 4,
|
19 |
+
"classifier_dropout": 0.0,
|
20 |
+
"d_model": 512,
|
21 |
+
"decoder_adaptor_tying_config": null,
|
22 |
+
"decoder_attention_heads": 8,
|
23 |
+
"decoder_ffn_dim": 2048,
|
24 |
+
"decoder_layerdrop": 0.0,
|
25 |
+
"decoder_layers": 6,
|
26 |
+
"decoder_tying_config": null,
|
27 |
+
"deep_adaptor_tuning": false,
|
28 |
+
"deep_adaptor_tuning_ffn_only": false,
|
29 |
+
"dropout": 0.1,
|
30 |
+
"embed_low_rank_dim": 0,
|
31 |
+
"encoder_adaptor_tying_config": null,
|
32 |
+
"encoder_attention_heads": 8,
|
33 |
+
"encoder_ffn_dim": 2048,
|
34 |
+
"encoder_layerdrop": 0.0,
|
35 |
+
"encoder_layers": 6,
|
36 |
+
"encoder_tying_config": null,
|
37 |
+
"eos_token_id": 64001,
|
38 |
+
"expert_ffn_size": 128,
|
39 |
+
"features_embed_dims": null,
|
40 |
+
"features_vocab_sizes": null,
|
41 |
+
"gradient_checkpointing": false,
|
42 |
+
"gradient_reversal_for_domain_classifier": false,
|
43 |
+
"hypercomplex": false,
|
44 |
+
"hypercomplex_n": 2,
|
45 |
+
"ia3_adaptors": false,
|
46 |
+
"init_std": 0.02,
|
47 |
+
"initialization_scheme": "static",
|
48 |
+
"is_encoder_decoder": true,
|
49 |
+
"layernorm_adaptor_input": false,
|
50 |
+
"layernorm_prompt_projection": false,
|
51 |
+
"lora_adaptor_rank": 2,
|
52 |
+
"lora_adaptors": false,
|
53 |
+
"max_position_embeddings": 1024,
|
54 |
+
"mid_fusion_layers": 3,
|
55 |
+
"model_type": "mbart",
|
56 |
+
"moe_adaptors": false,
|
57 |
+
"multi_source": false,
|
58 |
+
"multi_source_method": null,
|
59 |
+
"multilayer_softmaxing": null,
|
60 |
+
"no_embed_norm": false,
|
61 |
+
"no_positional_encoding_decoder": false,
|
62 |
+
"no_positional_encoding_encoder": false,
|
63 |
+
"no_projection_prompt": false,
|
64 |
+
"no_scale_attention_embedding": false,
|
65 |
+
"num_domains_for_domain_classifier": 1,
|
66 |
+
"num_experts": 8,
|
67 |
+
"num_hidden_layers": 6,
|
68 |
+
"num_moe_adaptor_experts": 4,
|
69 |
+
"num_prompts": 100,
|
70 |
+
"num_sparsify_blocks": 8,
|
71 |
+
"pad_token_id": 0,
|
72 |
+
"parallel_adaptors": false,
|
73 |
+
"positional_encodings": false,
|
74 |
+
"postnorm_decoder": false,
|
75 |
+
"postnorm_encoder": false,
|
76 |
+
"prompt_dropout": 0.1,
|
77 |
+
"prompt_init_std": 0.02,
|
78 |
+
"prompt_projection_hidden_size": 4096,
|
79 |
+
"prompt_tuning": false,
|
80 |
+
"recurrent_projections": 1,
|
81 |
+
"residual_connection_adaptor": false,
|
82 |
+
"residual_connection_prompt": false,
|
83 |
+
"rope_encoding": false,
|
84 |
+
"scale_embedding": false,
|
85 |
+
"softmax_bias_tuning": false,
|
86 |
+
"softmax_temperature": 1.0,
|
87 |
+
"sparsification_temperature": 3.0,
|
88 |
+
"sparsify_attention": false,
|
89 |
+
"sparsify_ffn": false,
|
90 |
+
"target_vocab_size": 0,
|
91 |
+
"temperature_calibration": false,
|
92 |
+
"tokenizer_class": "AlbertTokenizer",
|
93 |
+
"transformers_version": "4.3.2",
|
94 |
+
"unidirectional_encoder": false,
|
95 |
+
"use_cache": true,
|
96 |
+
"use_moe": false,
|
97 |
+
"use_tanh_activation_prompt": false,
|
98 |
+
"vocab_size": 64053,
|
99 |
+
"wait_k": -1
|
100 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48632f5a00ab782f08f798d0e2f52ef26760dd91c52de2284bc10a2d1930f1f1
|
3 |
+
size 312313135
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<s>", "</s>", "<2acf>", "<2eng>", "<2fra>", "<2aoa>", "<2bah>", "<2brc>", "<2bzj>", "<2bzk>", "<2cab>", "<2cri>", "<2crs>", "<2dcr>", "<2djk>", "<2ara>", "<2ceb>", "<2deu>", "<2nep>", "<2zho>", "<2fab>", "<2fng>", "<2fpe>", "<2gcf>", "<2gcr>", "<2gpe>", "<2gul>", "<2gyn>", "<2hat>", "<2aze>", "<2icr>", "<2jam>", "<2kea>", "<2spa>", "<2kri>", "<2ktu>", "<2lou>", "<2mart1259>", "<2mfe>", "<2mue>", "<2pap>", "<2por>", "<2pcm>", "<2pov>", "<2pre>", "<2rcf>", "<2sag>", "<2srm>", "<2srn>", "<2svc>", "<2tpi>", "<2trf>", "<2wes>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d4d2a89008ec4276abf272279f9cf555aa7748c02e26db5ce7669c55dcafeec
|
3 |
+
size 1366394
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "use_fast": false, "strip_accents": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/share03/draj/data/parallel_corpora/creole/creolemt/naacl/albert-all64k"}
|