system HF staff commited on
Commit
6586570
1 Parent(s): 34767d1

Commit From AutoTrain

Browse files
.gitattributes CHANGED
@@ -32,3 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
36
+ *.tar.gz filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - summarization
5
+ language:
6
+ - unk
7
+ widget:
8
+ - text: "I love AutoTrain 🤗"
9
+ datasets:
10
+ - DmitriyVasiliev/autotrain-data-mbart-dia
11
+ co2_eq_emissions:
12
+ emissions: 5.176017928528579
13
+ ---
14
+
15
+ # Model Trained Using AutoTrain
16
+
17
+ - Problem type: Summarization
18
+ - Model ID: 55472129249
19
+ - CO2 Emissions (in grams): 5.1760
20
+
21
+ ## Validation Metrics
22
+
23
+ - Loss: 1.577
24
+ - Rouge1: 4.668
25
+ - Rouge2: 1.833
26
+ - RougeL: 4.650
27
+ - RougeLsum: 4.667
28
+ - Gen Len: 33.162
29
+
30
+ ## Usage
31
+
32
+ You can use cURL to access this model:
33
+
34
+ ```
35
+ $ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/DmitriyVasiliev/autotrain-mbart-dia-55472129249
36
+ ```
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "AutoTrain",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 12,
18
+ "decoder_start_token_id": 250021,
19
+ "dropout": 0.1,
20
+ "encoder_attention_heads": 16,
21
+ "encoder_ffn_dim": 4096,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 12,
24
+ "eos_token_id": 2,
25
+ "extra_pos_embeddings": 2,
26
+ "force_bos_token_to_be_generated": false,
27
+ "forced_eos_token_id": 2,
28
+ "init_std": 0.02,
29
+ "is_encoder_decoder": true,
30
+ "max_length": 200,
31
+ "max_position_embeddings": 1024,
32
+ "model_type": "mbart",
33
+ "normalize_before": true,
34
+ "normalize_embedding": true,
35
+ "num_beams": 5,
36
+ "num_hidden_layers": 12,
37
+ "output_past": true,
38
+ "pad_token_id": 1,
39
+ "scale_embedding": true,
40
+ "static_position_embeddings": false,
41
+ "tie_word_embeddings": false,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.28.1",
44
+ "use_cache": true,
45
+ "vocab_size": 250027
46
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 250021,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "max_length": 200,
7
+ "num_beams": 5,
8
+ "pad_token_id": 1,
9
+ "transformers_version": "4.28.1"
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b7be66e3aff2aef41fb33050c8bb2e5987fe94f5315212916acc80c726ff56
3
+ size 3468694113
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 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN"
28
+ ],
29
+ "bos_token": "<s>",
30
+ "cls_token": "<s>",
31
+ "eos_token": "</s>",
32
+ "mask_token": "<mask>",
33
+ "pad_token": "<pad>",
34
+ "sep_token": "</s>",
35
+ "unk_token": "<unk>"
36
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:596c5a4c6d3f1a30908406c2b02396ed0a927c18342237b32ac8bd2fff7322a3
3
+ size 17103694
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 1024,
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "src_lang": "en_XX",
20
+ "tgt_lang": "ru_RU",
21
+ "tokenizer_class": "MBartTokenizer",
22
+ "unk_token": "<unk>"
23
+ }