lysandre HF staff commited on
Commit
dabc149
1 Parent(s): f65782f

Add model and configuration.

Browse files
Files changed (2) hide show
  1. config.json +97 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "attention_dropout": 0.1,
5
+ "bos_token_id": 0,
6
+ "d_model": 16,
7
+ "decoder": {
8
+ "_name_or_path": "",
9
+ "add_cross_attention": false,
10
+ "architectures": null,
11
+ "bad_words_ids": null,
12
+ "bos_token_id": 2,
13
+ "chunk_size_feed_forward": 0,
14
+ "decoder_start_token_id": null,
15
+ "diversity_penalty": 0.0,
16
+ "do_sample": false,
17
+ "early_stopping": false,
18
+ "encoder_no_repeat_ngram_size": 0,
19
+ "eos_token_id": null,
20
+ "finetuning_task": null,
21
+ "forced_bos_token_id": null,
22
+ "forced_eos_token_id": null,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1"
26
+ },
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "length_penalty": 1.0,
34
+ "max_length": 20,
35
+ "min_length": 0,
36
+ "model_type": "fsmt_decoder",
37
+ "no_repeat_ngram_size": 0,
38
+ "num_beam_groups": 1,
39
+ "num_beams": 1,
40
+ "num_return_sequences": 1,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "output_scores": false,
44
+ "pad_token_id": null,
45
+ "prefix": null,
46
+ "problem_type": null,
47
+ "pruned_heads": {},
48
+ "remove_invalid_values": false,
49
+ "repetition_penalty": 1.0,
50
+ "return_dict": true,
51
+ "return_dict_in_generate": false,
52
+ "sep_token_id": null,
53
+ "task_specific_params": null,
54
+ "temperature": 1.0,
55
+ "tie_encoder_decoder": false,
56
+ "tie_word_embeddings": true,
57
+ "tokenizer_class": null,
58
+ "top_k": 50,
59
+ "top_p": 1.0,
60
+ "torch_dtype": null,
61
+ "torchscript": false,
62
+ "transformers_version": "4.10.0.dev0",
63
+ "use_bfloat16": false,
64
+ "vocab_size": 99
65
+ },
66
+ "decoder_attention_heads": 4,
67
+ "decoder_ffn_dim": 4,
68
+ "decoder_layerdrop": 0.0,
69
+ "decoder_layers": 2,
70
+ "decoder_start_token_id": 2,
71
+ "dropout": 0.1,
72
+ "encoder_attention_heads": 4,
73
+ "encoder_ffn_dim": 4,
74
+ "encoder_layerdrop": 0.0,
75
+ "encoder_layers": 2,
76
+ "eos_token_id": 2,
77
+ "forced_eos_token_id": 2,
78
+ "init_std": 0.02,
79
+ "is_encoder_decoder": true,
80
+ "langs": [
81
+ "ru",
82
+ "en"
83
+ ],
84
+ "max_length": 200,
85
+ "max_position_embeddings": 20,
86
+ "model_type": "fsmt",
87
+ "num_beams": 5,
88
+ "num_hidden_layers": 2,
89
+ "pad_token_id": 1,
90
+ "scale_embedding": true,
91
+ "src_vocab_size": 99,
92
+ "tgt_vocab_size": 99,
93
+ "tie_word_embeddings": false,
94
+ "transformers_version": null,
95
+ "use_cache": true,
96
+ "vocab_size": 99
97
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f0f907b433356ab14656c6453f6cff3bb8ef2180b6a6d505076733f3990902
3
+ size 144993