ybelkada HF staff commited on
Commit
39a22a8
1 Parent(s): 0c2c2ec

Upload FSMTForConditionalGeneration

Browse files
Files changed (2) hide show
  1. config.json +109 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "6a1a981b29c8a98c1fd31bd0ad809f5575ca6c7a",
3
+ "_name_or_path": "hf-internal-testing/tiny-random-FSMTForConditionalGeneration",
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "FSMTForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 0,
11
+ "d_model": 16,
12
+ "decoder": {
13
+ "_name_or_path": "",
14
+ "add_cross_attention": false,
15
+ "architectures": null,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 2,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": null,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "is_decoder": false,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "length_penalty": 1.0,
42
+ "max_length": 20,
43
+ "min_length": 0,
44
+ "model_type": "fsmt_decoder",
45
+ "no_repeat_ngram_size": 0,
46
+ "num_beam_groups": 1,
47
+ "num_beams": 1,
48
+ "num_return_sequences": 1,
49
+ "output_attentions": false,
50
+ "output_hidden_states": false,
51
+ "output_scores": false,
52
+ "pad_token_id": null,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "remove_invalid_values": false,
57
+ "repetition_penalty": 1.0,
58
+ "return_dict": true,
59
+ "return_dict_in_generate": false,
60
+ "sep_token_id": null,
61
+ "suppress_tokens": null,
62
+ "task_specific_params": null,
63
+ "temperature": 1.0,
64
+ "tf_legacy_loss": false,
65
+ "tie_encoder_decoder": false,
66
+ "tie_word_embeddings": true,
67
+ "tokenizer_class": null,
68
+ "top_k": 50,
69
+ "top_p": 1.0,
70
+ "torch_dtype": null,
71
+ "torchscript": false,
72
+ "transformers_version": "4.25.1",
73
+ "typical_p": 1.0,
74
+ "use_bfloat16": false,
75
+ "vocab_size": 31232
76
+ },
77
+ "decoder_attention_heads": 4,
78
+ "decoder_ffn_dim": 4,
79
+ "decoder_layerdrop": 0.0,
80
+ "decoder_layers": 2,
81
+ "decoder_start_token_id": 2,
82
+ "dropout": 0.1,
83
+ "encoder_attention_heads": 4,
84
+ "encoder_ffn_dim": 4,
85
+ "encoder_layerdrop": 0.0,
86
+ "encoder_layers": 2,
87
+ "eos_token_id": 2,
88
+ "forced_eos_token_id": 2,
89
+ "init_std": 0.02,
90
+ "is_encoder_decoder": true,
91
+ "langs": [
92
+ "ru",
93
+ "en"
94
+ ],
95
+ "max_length": 200,
96
+ "max_position_embeddings": 20,
97
+ "model_type": "fsmt",
98
+ "num_beams": 5,
99
+ "num_hidden_layers": 2,
100
+ "pad_token_id": 1,
101
+ "scale_embedding": true,
102
+ "src_vocab_size": 31640,
103
+ "tgt_vocab_size": 31232,
104
+ "tie_word_embeddings": false,
105
+ "torch_dtype": "float32",
106
+ "transformers_version": null,
107
+ "use_cache": true,
108
+ "vocab_size": 31640
109
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eabc700ae628b0c1f66e6bd37a7108efa3ea0e437a972ec095287428ef99a647
3
+ size 4081075