Hugging Face's logo

lindazeng979
/
codemixed-sentiment-models

Text Classification
Transformers
Safetensors
English
Spanish
Malayalam
sentiment-analysis
code-switching
code-mixed
data-augmentation
llm-augmentation
spanglish
spanish-english
malayalam-english
mbert
xlm-roberta
xlm-t
low-resource
Model card Files
xet
 Community
lindazeng979 commited on
Commit
75c8ded
·
verified ·
1 Parent(s): 2c75849

Add important-models

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +14 -0
  2. important-models/Malayalam-English Models/ma_MIX_XLMT/config.json +40 -0
  3. important-models/Malayalam-English Models/ma_MIX_XLMT/model.safetensors +3 -0
  4. important-models/Malayalam-English Models/ma_MIX_tokenizer/sentencepiece.bpe.model +3 -0
  5. important-models/Malayalam-English Models/ma_MIX_tokenizer/special_tokens_map.json +15 -0
  6. important-models/Malayalam-English Models/ma_MIX_tokenizer/tokenizer.json +3 -0
  7. important-models/Malayalam-English Models/ma_MIX_tokenizer/tokenizer_config.json +55 -0
  8. important-models/Malayalam-English Models/ma_NCM_XLMT/config.json +40 -0
  9. important-models/Malayalam-English Models/ma_NCM_XLMT/model.safetensors +3 -0
  10. important-models/Malayalam-English Models/ma_NCM_tokenizer/sentencepiece.bpe.model +3 -0
  11. important-models/Malayalam-English Models/ma_NCM_tokenizer/special_tokens_map.json +15 -0
  12. important-models/Malayalam-English Models/ma_NCM_tokenizer/tokenizer.json +3 -0
  13. important-models/Malayalam-English Models/ma_NCM_tokenizer/tokenizer_config.json +55 -0
  14. important-models/Malayalam-English Models/ma_SCM_XLMT/config.json +40 -0
  15. important-models/Malayalam-English Models/ma_SCM_XLMT/model.safetensors +3 -0
  16. important-models/Malayalam-English Models/ma_SCM_tokenizer/sentencepiece.bpe.model +3 -0
  17. important-models/Malayalam-English Models/ma_SCM_tokenizer/special_tokens_map.json +15 -0
  18. important-models/Malayalam-English Models/ma_SCM_tokenizer/tokenizer.json +3 -0
  19. important-models/Malayalam-English Models/ma_SCM_tokenizer/tokenizer_config.json +55 -0
  20. important-models/Reduced Spanglish Models/resp_MIX_XLMT/config.json +42 -0
  21. important-models/Reduced Spanglish Models/resp_MIX_XLMT/model.safetensors +3 -0
  22. important-models/Reduced Spanglish Models/resp_MIX_tokenizer/special_tokens_map.json +7 -0
  23. important-models/Reduced Spanglish Models/resp_MIX_tokenizer/tokenizer.json +0 -0
  24. important-models/Reduced Spanglish Models/resp_MIX_tokenizer/tokenizer_config.json +55 -0
  25. important-models/Reduced Spanglish Models/resp_MIX_tokenizer/vocab.txt +0 -0
  26. important-models/Reduced Spanglish Models/resp_NCM_XLMT/config.json +42 -0
  27. important-models/Reduced Spanglish Models/resp_NCM_XLMT/model.safetensors +3 -0
  28. important-models/Reduced Spanglish Models/resp_NCM_tokenizer/special_tokens_map.json +7 -0
  29. important-models/Reduced Spanglish Models/resp_NCM_tokenizer/tokenizer.json +0 -0
  30. important-models/Reduced Spanglish Models/resp_NCM_tokenizer/tokenizer_config.json +55 -0
  31. important-models/Reduced Spanglish Models/resp_NCM_tokenizer/vocab.txt +0 -0
  32. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_10k/config.json +40 -0
  33. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_10k/model.safetensors +3 -0
  34. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex-08t/config.json +40 -0
  35. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex-08t/model.safetensors +3 -0
  36. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex-small/config.json +40 -0
  37. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex-small/model.safetensors +3 -0
  38. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex/config.json +40 -0
  39. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex/model.safetensors +3 -0
  40. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_15k/config.json +40 -0
  41. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_15k/model.safetensors +3 -0
  42. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_25k_5e-7/config.json +40 -0
  43. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_25k_5e-7/model.safetensors +3 -0
  44. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_500ex/config.json +40 -0
  45. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_500ex/model.safetensors +3 -0
  46. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_50ex/config.json +40 -0
  47. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_50ex/model.safetensors +3 -0
  48. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_50k_5e-7/config.json +40 -0
  49. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_50k_5e-7/model.safetensors +3 -0
  50. important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_5k/config.json +40 -0
.gitattributes CHANGED
@@ -85,3 +85,17 @@ malayalam-English/zero-shot/XLM-T/malay_zero_shot_tokenizer_XLMT/tokenizer.json
85
  malayalam-English/zero-shot/XLM-T/malay_zero_shot_tokenizer_XLMT_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
86
  malayalam-english/zero-shot/XLM-T/malay_zero_shot_tokenizer_XLMT/tokenizer.json filter=lfs diff=lfs merge=lfs -text
87
  malayalam-english/zero-shot/XLM-T/malay_zero_shot_tokenizer_XLMT_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
  malayalam-English/zero-shot/XLM-T/malay_zero_shot_tokenizer_XLMT_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
86
  malayalam-english/zero-shot/XLM-T/malay_zero_shot_tokenizer_XLMT/tokenizer.json filter=lfs diff=lfs merge=lfs -text
87
  malayalam-english/zero-shot/XLM-T/malay_zero_shot_tokenizer_XLMT_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
88
+ important-models/Malayalam-English[[:space:]]Models/ma_MIX_tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
89
+ important-models/Malayalam-English[[:space:]]Models/ma_NCM_tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
90
+ important-models/Malayalam-English[[:space:]]Models/ma_SCM_tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
91
+ important-models/Spanglish[[:space:]]Models/spanglish_MIX_tokenizer_XLMT_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text
92
+ important-models/Spanglish[[:space:]]Models/spanglish_MIX_tokenizer_XLMT_15-shot/tokenizer.json filter=lfs diff=lfs merge=lfs -text
93
+ important-models/Spanglish[[:space:]]Models/spanglish_MIX_tokenizer_XLMT_150ex/tokenizer.json filter=lfs diff=lfs merge=lfs -text
94
+ important-models/Spanglish[[:space:]]Models/spanglish_MIX_tokenizer_XLMT_150ex-08t/tokenizer.json filter=lfs diff=lfs merge=lfs -text
95
+ important-models/Spanglish[[:space:]]Models/spanglish_MIX_tokenizer_XLMT_150ex-small/tokenizer.json filter=lfs diff=lfs merge=lfs -text
96
+ important-models/Spanglish[[:space:]]Models/spanglish_MIX_tokenizer_XLMT_500ex/tokenizer.json filter=lfs diff=lfs merge=lfs -text
97
+ important-models/Spanglish[[:space:]]Models/spanglish_MIX_tokenizer_XLMT_50ex/tokenizer.json filter=lfs diff=lfs merge=lfs -text
98
+ important-models/Spanglish[[:space:]]Models/spanglish_MIX_tokenizer_XLMT_50k_5e-7/tokenizer.json filter=lfs diff=lfs merge=lfs -text
99
+ important-models/Spanglish[[:space:]]Models/spanglish_MIX_tokenizer_XLMT_5k/tokenizer.json filter=lfs diff=lfs merge=lfs -text
100
+ important-models/Spanglish[[:space:]]Models/spanglish_MIX_tokenizer_XLMT_stages/tokenizer.json filter=lfs diff=lfs merge=lfs -text
101
+ important-models/Spanglish[[:space:]]Models/spanglish_SCM_tokenizer_XLMT-15k/tokenizer.json filter=lfs diff=lfs merge=lfs -text
important-models/Malayalam-English Models/ma_MIX_XLMT/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Malayalam-English Models/ma_MIX_XLMT/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9dba3de238b2121f017b52463a671d8eba3c577205dce83fae53ab9fe2be709
3
+ size 1112208084
important-models/Malayalam-English Models/ma_MIX_tokenizer/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
important-models/Malayalam-English Models/ma_MIX_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
important-models/Malayalam-English Models/ma_MIX_tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f4fe57cb49634fbb8ce0dde9ac48db790bcce8a3a9c28462bb4f69c0517f48
3
+ size 17098525
important-models/Malayalam-English Models/ma_MIX_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
important-models/Malayalam-English Models/ma_NCM_XLMT/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Malayalam-English Models/ma_NCM_XLMT/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e98a6bef4f8f05ceb7df75f77ce29bebe7da92ebb1b21091dd5fad8657a208
3
+ size 1112208084
important-models/Malayalam-English Models/ma_NCM_tokenizer/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
important-models/Malayalam-English Models/ma_NCM_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
important-models/Malayalam-English Models/ma_NCM_tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f4fe57cb49634fbb8ce0dde9ac48db790bcce8a3a9c28462bb4f69c0517f48
3
+ size 17098525
important-models/Malayalam-English Models/ma_NCM_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
important-models/Malayalam-English Models/ma_SCM_XLMT/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Malayalam-English Models/ma_SCM_XLMT/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f74647f748e2f4770551371276fe6fa56747353055cf4f52153522e3030f1b
3
+ size 1112208084
important-models/Malayalam-English Models/ma_SCM_tokenizer/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
important-models/Malayalam-English Models/ma_SCM_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
important-models/Malayalam-English Models/ma_SCM_tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f4fe57cb49634fbb8ce0dde9ac48db790bcce8a3a9c28462bb4f69c0517f48
3
+ size 17098525
important-models/Malayalam-English Models/ma_SCM_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
important-models/Reduced Spanglish Models/resp_MIX_XLMT/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.5,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.38.2",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 119547
42
+ }
important-models/Reduced Spanglish Models/resp_MIX_XLMT/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6899a751f0ac18a08a3b7ae077a453b65b51088d69ff4e08e4a678c31a854d9
3
+ size 711446532
important-models/Reduced Spanglish Models/resp_MIX_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
important-models/Reduced Spanglish Models/resp_MIX_tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
important-models/Reduced Spanglish Models/resp_MIX_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
important-models/Reduced Spanglish Models/resp_MIX_tokenizer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
important-models/Reduced Spanglish Models/resp_NCM_XLMT/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.5,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.38.2",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 119547
42
+ }
important-models/Reduced Spanglish Models/resp_NCM_XLMT/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4d7e68f76d52d52c48c31252bcd5d902c607a8568e1b451faf977478736f7e
3
+ size 711446532
important-models/Reduced Spanglish Models/resp_NCM_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
important-models/Reduced Spanglish Models/resp_NCM_tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
important-models/Reduced Spanglish Models/resp_NCM_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
important-models/Reduced Spanglish Models/resp_NCM_tokenizer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_10k/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_10k/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68b529bfbce2e05e2a502fcca77eec4fcdd4a2dd6cee3472e9895ac4ea55434
3
+ size 1112208084
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex-08t/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex-08t/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3dbd93c1fc054074f589a24cb4d460fe5ce73762f0fa81a7ebfe7be13db637
3
+ size 1112208084
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex-small/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex-small/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:966a79af6768347498afb459dc014f18eacd3a72917f199d1b76776ef4e92a0e
3
+ size 1112208084
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_150ex/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9bf78deaae116777105468060b317af8d891e14bf138b8a56fd134d28ad2ff
3
+ size 1112208084
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_15k/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_15k/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e6066684c055bfcbf8ad71ca98b36d17efe975422e74ff07f8a7acb608d4e4
3
+ size 1112208084
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_25k_5e-7/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_25k_5e-7/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d0d26ca69bcd3360bbd551d7a5be4396b87702240c96dc81b14e9b893203a0
3
+ size 1112208084
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_500ex/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_500ex/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7795687383ee992a14bd1f1bcd7d6bfba5b3f53dce99b9a24ca63fc363d48c38
3
+ size 1112208084
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_50ex/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_50ex/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd11d7046c76475ca54e42dc9135706f18d337145f16bb130b9202956aa0316
3
+ size 1112208084
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_50k_5e-7/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_50k_5e-7/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:244ebfb3bfe980dd50cb2bcf21f05215cb4841c7e1321b605f045c2f8819f5bf
3
+ size 1112208084
important-models/Spanglish Models/spanglish_MIX_mBERT_XLMT_5k/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.5,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "xlm-roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 250002
40
+ }