nbroad HF staff commited on
Commit
f874fe1
1 Parent(s): 1a6bb08

add config, vocab, merges

Browse files
Files changed (3) hide show
  1. config.json +100 -0
  2. merges.txt +0 -0
  3. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "FSMTForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "d_model": 1024,
10
+ "decoder": {
11
+ "_name_or_path": "",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "bad_words_ids": null,
15
+ "bos_token_id": 2,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "is_decoder": false,
32
+ "is_encoder_decoder": false,
33
+ "label2id": {
34
+ "LABEL_0": 0,
35
+ "LABEL_1": 1
36
+ },
37
+ "length_penalty": 1.0,
38
+ "max_length": 20,
39
+ "min_length": 0,
40
+ "model_type": "fsmt_decoder",
41
+ "no_repeat_ngram_size": 0,
42
+ "num_beam_groups": 1,
43
+ "num_beams": 1,
44
+ "num_return_sequences": 1,
45
+ "output_attentions": false,
46
+ "output_hidden_states": false,
47
+ "output_scores": false,
48
+ "pad_token_id": null,
49
+ "prefix": null,
50
+ "problem_type": null,
51
+ "pruned_heads": {},
52
+ "remove_invalid_values": false,
53
+ "repetition_penalty": 1.0,
54
+ "return_dict": true,
55
+ "return_dict_in_generate": false,
56
+ "sep_token_id": null,
57
+ "task_specific_params": null,
58
+ "temperature": 1.0,
59
+ "tie_encoder_decoder": false,
60
+ "tie_word_embeddings": true,
61
+ "tokenizer_class": null,
62
+ "top_k": 50,
63
+ "top_p": 1.0,
64
+ "torch_dtype": null,
65
+ "torchscript": false,
66
+ "transformers_version": "4.16.2",
67
+ "use_bfloat16": false,
68
+ "vocab_size": 42024
69
+ },
70
+ "decoder_attention_heads": 16,
71
+ "decoder_ffn_dim": 4096,
72
+ "decoder_layerdrop": 0,
73
+ "decoder_layers": 6,
74
+ "decoder_start_token_id": 2,
75
+ "dropout": 0.0,
76
+ "encoder_attention_heads": 16,
77
+ "encoder_ffn_dim": 4096,
78
+ "encoder_layerdrop": 0,
79
+ "encoder_layers": 6,
80
+ "eos_token_id": 2,
81
+ "forced_eos_token_id": 2,
82
+ "init_std": 0.02,
83
+ "is_encoder_decoder": true,
84
+ "langs": [
85
+ "src",
86
+ "trg"
87
+ ],
88
+ "max_length": 200,
89
+ "max_position_embeddings": 1024,
90
+ "model_type": "fsmt",
91
+ "num_beams": 5,
92
+ "num_hidden_layers": 6,
93
+ "pad_token_id": 1,
94
+ "scale_embedding": true,
95
+ "src_vocab_size": 64871,
96
+ "tgt_vocab_size": 64871,
97
+ "tie_word_embeddings": true,
98
+ "transformers_version": null,
99
+ "use_cache": true
100
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt ADDED
The diff for this file is too large to render. See raw diff