Hugging Face's logo

Spaces:
Alifjo123
/
RobertaBaseModel-messaging
Running

App Files Community
Alifnewjourney Jovani safik commited on
Commit
03c1bd0
·
1 Parent(s): 1514952

add app.py, model folders, and requirements for Hugging Face Space

Browse files
Files changed (17) hide show
  1. app.py +4 -0
  2. final_model_roberta_contextual_22k/config.json +35 -0
  3. final_model_roberta_contextual_22k/merges.txt +0 -0
  4. final_model_roberta_contextual_22k/model.safetensors +3 -0
  5. final_model_roberta_contextual_22k/special_tokens_map.json +15 -0
  6. final_model_roberta_contextual_22k/tokenizer.json +0 -0
  7. final_model_roberta_contextual_22k/tokenizer_config.json +58 -0
  8. final_model_roberta_contextual_22k/vocab.json +0 -0
  9. final_model_roberta_contextual_22k_2/config.json +35 -0
  10. final_model_roberta_contextual_22k_2/merges.txt +0 -0
  11. final_model_roberta_contextual_22k_2/model.safetensors +3 -0
  12. final_model_roberta_contextual_22k_2/special_tokens_map.json +15 -0
  13. final_model_roberta_contextual_22k_2/tokenizer.json +0 -0
  14. final_model_roberta_contextual_22k_2/tokenizer_config.json +58 -0
  15. final_model_roberta_contextual_22k_2/vocab.json +0 -0
  16. flagged/dataset1.csv +2 -0
  17. requirements.txt +3 -0
app.py ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ from transformers import RobertaTokenizerFast
2
+
3
+ tokenizer = RobertaTokenizerFast.from_pretrained("roberta-base") # atau model awalmu
4
+ tokenizer.save_pretrained("final_model_roberta_contextual_22k_2")
final_model_roberta_contextual_22k/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "WeightedRobertaForSentiment"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Safe",
14
+ "1": "Unsafe"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "Safe": 0,
20
+ "Unsafe": 1
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 514,
24
+ "model_type": "roberta",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 1,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.54.1",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 50265
35
+ }
final_model_roberta_contextual_22k/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
final_model_roberta_contextual_22k/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9accafc1a03d94c15afa1afe52b960367dc189ae2bba3dfa8d3e2923ff209dc6
3
+ size 498612912
final_model_roberta_contextual_22k/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
+ }
final_model_roberta_contextual_22k/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
final_model_roberta_contextual_22k/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
final_model_roberta_contextual_22k/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
final_model_roberta_contextual_22k_2/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "WeightedRobertaForSentiment"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Safe",
14
+ "1": "Unsafe"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "Safe": 0,
20
+ "Unsafe": 1
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 514,
24
+ "model_type": "roberta",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 1,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.54.1",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 50265
35
+ }
final_model_roberta_contextual_22k_2/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
final_model_roberta_contextual_22k_2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db06d3ec58897ac52904e0cb47f5747bcb8b8ff1d9ff0c4c937a6a2e74895a2f
3
+ size 498612912
final_model_roberta_contextual_22k_2/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
+ }
final_model_roberta_contextual_22k_2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
final_model_roberta_contextual_22k_2/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
final_model_roberta_contextual_22k_2/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
flagged/dataset1.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ 💬 Input Text,Prediction,Confidence,timestamp
2
+ hallo,✅ Safe (87.48% confidence),"{""Safe"": 0.8747963905334473, ""Unsafe"": 0.12520363926887512}",2025-07-31 11:06:57.397397
requirements.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ transformers
2
+ torch
3
+ gradio