katopz commited on
Commit
b4bd212
1 Parent(s): b63967c

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "return_dict": true,
3
+ "output_hidden_states": false,
4
+ "output_attentions": false,
5
+ "torchscript": false,
6
+ "torch_dtype": "float32",
7
+ "use_bfloat16": false,
8
+ "tf_legacy_loss": false,
9
+ "pruned_heads": {},
10
+ "tie_word_embeddings": true,
11
+ "is_encoder_decoder": false,
12
+ "is_decoder": false,
13
+ "cross_attention_hidden_size": null,
14
+ "add_cross_attention": false,
15
+ "tie_encoder_decoder": false,
16
+ "max_length": 20,
17
+ "min_length": 0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "num_beams": 1,
21
+ "num_beam_groups": 1,
22
+ "diversity_penalty": 0.0,
23
+ "temperature": 1.0,
24
+ "top_k": 50,
25
+ "top_p": 1.0,
26
+ "typical_p": 1.0,
27
+ "repetition_penalty": 1.0,
28
+ "length_penalty": 1.0,
29
+ "no_repeat_ngram_size": 0,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "bad_words_ids": null,
32
+ "num_return_sequences": 1,
33
+ "chunk_size_feed_forward": 0,
34
+ "output_scores": false,
35
+ "return_dict_in_generate": false,
36
+ "forced_bos_token_id": null,
37
+ "forced_eos_token_id": null,
38
+ "remove_invalid_values": false,
39
+ "exponential_decay_length_penalty": null,
40
+ "suppress_tokens": null,
41
+ "begin_suppress_tokens": null,
42
+ "architectures": [
43
+ "XLMRobertaModel"
44
+ ],
45
+ "finetuning_task": null,
46
+ "id2label": {
47
+ "0": "LABEL_0",
48
+ "1": "LABEL_1"
49
+ },
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "tokenizer_class": null,
55
+ "prefix": null,
56
+ "bos_token_id": 0,
57
+ "pad_token_id": 1,
58
+ "eos_token_id": 2,
59
+ "sep_token_id": null,
60
+ "decoder_start_token_id": null,
61
+ "task_specific_params": null,
62
+ "problem_type": null,
63
+ "_name_or_path": "/Users/katopz/.cache/huggingface/hub/models--intfloat--multilingual-e5-large/snapshots/9f78368af0062735ba99812349c562316e29f719",
64
+ "transformers_version": "4.36.2",
65
+ "model_type": "xlm-roberta",
66
+ "output_past": true,
67
+ "vocab_size": 250002,
68
+ "hidden_size": 1024,
69
+ "num_hidden_layers": 24,
70
+ "num_attention_heads": 16,
71
+ "hidden_act": "gelu",
72
+ "intermediate_size": 4096,
73
+ "hidden_dropout_prob": 0.1,
74
+ "attention_probs_dropout_prob": 0.1,
75
+ "max_position_embeddings": 514,
76
+ "type_vocab_size": 1,
77
+ "initializer_range": 0.02,
78
+ "layer_norm_eps": 1e-05,
79
+ "position_embedding_type": "absolute",
80
+ "use_cache": true,
81
+ "classifier_dropout": null
82
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
3
+ size 17082756
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
weights.00.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47f093c865523c47ef618a887528f4fd16677a911e00e5715c0db14e6745105d
3
+ size 1119826785