tejesh916K commited on
Commit
e429a52
·
1 Parent(s): d82a2c9

feat: include fine-tuned MuRIL model for production detection

Browse files
.gitattributes ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
2
+ *.bin filter=lfs diff=lfs merge=lfs -text
data/secure_words.bin CHANGED
@@ -1 +1,3 @@
1
- ZG9uZ2EKdmVkaGF2YQp2ZWRhdmEKcGFuZGkKa3Vra2EKbmVlIGFtbWEKbmVlIGFiYmEKY2hhdHRhCndhc3RlIGZlbGxvdwppdGVtCmxvdyBjbGFzcwpwaWNjaGkKZXJyaXBhcHBhCmVycmkKbXVuZGFtb3BpCmRhcmlkcnlhCnNhbmkKcGFuaWtpIG1hbGluYQp0aGlra2EKd29yc3QgZmVsbG93CmJsb29keSBmb29sCnVzZWxlc3MgZmVsbG93CmxhbmphCmxhbmpha29kYWthCmxhbmphIGtvZGFrYQptdW5kYQptb2RkYQpkZW5ndQpkZW5nZXkKZGVuZ3V0aGEKbmVlIHlhYmJhCmNoYXZhdGEKc2FubmFzaQpsdWNjaGEKaG93bGUKcHVrdQpwdWsKbWFkZGEKbGF2YWRhCmtvamphCmhpanJhCmJvY2NodQpuZSB5YW1tYQpuZSBheXlhCmJva3UKYmFkY293CmVycmkgcHVrdQpwaWNoaSBsYW5qYWtvZGFrYQpib2t1bG8KZ3VkZGEKbXVzYWxpCm5pIGJvbmRoYQpuaSBhYmJhCmNoZXR0YW5hIGtvZGFrYQpkdXJtYXJndWR1Cm5lZSBheXlhCmNoYXR0YSBuYSBrb2Rha2EKcGljaGkgcHVsa2EKZXJyaSBwdXNocGFtCndhc3RlIGdhZHUKbmUga2FtbWEKd2FzdGUgbmEga29kYWthCnBvcmFtYm9rdQpzaWdndSBsZW5pCmxhamphCnllcnJpCmJld2Fyc2kKYmV3YXJzCnBha29kaQpwdWxrYQpidWZmb29uCnNjb3VuZHJlbApyYXNjYWwKaWRpb3QKc3R1cGlkCmxvc2VyCmxvYWZlcgpyb3dkeQo0MjAKZG9uZ2FuYSBrb2Rha2EKbmVlIGZ1a3UKa29uZGEgZXJyaQpwb29rCnBvb2t1Cm1vZGRhbG8KbGF2YWRhbG8Kc3VsbGkKc3VsbGlnYQpsYWJvciBuYSBrb2Rha2EKY2hhcHJpCmNoYXByaSBnYWR1CmVycmlob29rCmhvb2sgZ2FkdQpiaGFkY293CmJoYWRrYXcKaG93bGEKamFmZmEKZ2FqdWxhdGhvCmtvamphIG5hIGtvZGFrYQpzaGlrYW5kaQpmYWtlIGdhZHUKZnJhdWQgZ2FkdQpkdW5uYXBvdGh1CmdhYWRpZGEKZ2FkaWRhCmJ1ZmZhbG8KbW9ua2V5CmtvdGhpCmtvdGhpIHZlZGhhdmEKc29sbHUKc29sdQpzb2xsdSBnYWR1CnZhZGh1cmEKb2RpeWFtbWEKeWFkYXZhCnllZGF2YQp0dWR1bXUKd2FzdGUgYm9keQpjaGV0aGEKY2hldHRhCnBlbmR1CnRyYXNoCmdhcmJhZ2UKZGlydHkgZmVsbG93Cm5hc3R5CmNoZWFwIGZlbGxvdwpsb3cgY2xhc3MgZmVsbG93CnRoaXJkIGNsYXNzCjNyZCBjbGFzcwo0dGggY2xhc3MKbWVudGFsbwpwc3ljaG8Kc2FkaXN0CnRodXB1awp3b3JzdCBnYWR1CnBpY2hpIG5hIGtvZGFrYQplcnJpIG5hIGtvZGFrYQpkb25nYSBuYSBrb2Rha2EKZG9uZ2EgbXVuZGEKcmFua3UgbXVuZGEKYmF6YXJ1IG11bmRhCmJhemFyIGRhbmEKcm9hZCBtZWVkYSB0aWdlIGRhbmEKdGlydWd1Ym90aHUKdGhpcnVndWJvdGh1CnRhYWd1Ym90aHUKdGFndWJvdGh1Cmp1bGUKanVsYXlpCmF2YWxhbmphCmFkZGFtaW5hCmFkZGFtaW5hIHBhbnVsdQpuZWVrdSBlbmR1a3UgcmEKbmVla3UgZW5kdWt1Cm11c3Vrb25pIGt1cmNobwptdXN1a28Kc2h1dCB1cApjbG9zZSB5b3VyIG1vdXRoCm5vcnUgbXV5eWkKbm9ydSBtdXN1a28Kbm90bG8KZ3VkZGFsbwpiYXN0aGkKc2x1bQpzbHVtIGZlbGxvdwpsb2NhbCBnYWR1CnVuY2l2aWxpemVkCmJhcmJhcmlhbgpicnV0ZQpzYXZhZ2UKcmFrc2hhc3VkYQpyYWtzaGFzaQp3aXRjaApiaXRjaApzbHV0Cndob3JlCnByb3N0aXR1dGUKYmFzdGFyZAphc3Nob2xlCmZ1Y2tlcgptb3RoZXJmdWNrZXIKc2lzdGVyIGZ1Y2tlcgpicm90aGVyIGZ1Y2tlcgpmYXRoZXIgZnVja2VyCmRpY2sKY29jawpwdXNzeQpjdW50CnRpdHMKYm9vYnMKbmlwcGxlCnBlbmlzCnZhZ2luYQpmdWNrCmZ1Y2tpbmcKZnVja2VkCnNjcmV3ZWQKc2hhZ2dlZApodW1wZWQKY3JlYW1waWUKc3Blcm0Kc2VtZW4Kaml6egpzcHVuawpzcXVpcnQKaG9ybnkKcmFwZQptb2xlc3QKaGFyYXNzCmFzc2F1bHQKYWJ1c2UKdmlvbGF0ZQpkZWdyYWRlCmh1bWlsaWF0ZQpzdWljaWRlCmt5cwpjaG9rZQpzdHJhbmdsZQpzdWZmb2NhdGUKc2xhcApzcGl0CnNoaXQKZmlsdGgKZ3JpbWUKbXVjawpzbGltZQpzY3VtCnZlcm1pbgpwZXN0CnBhcmFzaXRlCmxlZWNoCm1hZ2dvdApqYWNrYXNzCm11bGUKb3gKYnVsbAp2dWx0dXJlCnNuYWtlCmxpemFyZApiYXN0aGkgZ2FkdQpiYXN0aGkgZmVsbG93CnJvYWQgZmVsbG93CnJvYWQgZ2FkdQpzdHJlZXQgZmVsbG93CnBhdmVtZW50IGZlbGxvdwpmb290cGF0aCBnYWR1CnNpZ25hbCBnYWR1CnRyYWZmaWMgZmVsbG93CmF1dG8gZ2FkdQpyaWtzaGEgZ2FkdQpjb29saWUKY29vbGllIGdhZHUKbGFib3IgZ2FkdQpzd2VlcGVyIGdhZHUKZ2FyYmFnZSBnYWR1CmR1c3RiaW4gZ2FkdQp0b2lsZXQgZ2FkdQpndXR0ZXIgZ2FkdQpkcmFpbiBnYWR1CnNld2VyIGdhZHUKbWFuaG9sZSBnYWR1Cm5lZSBpbnRsbwpuZWUgaW50aSB2YWx1Cm5lZSBmYW1pbHkKbmVlIHBhcmVudHMKbmVlIGZhdGhlcgpuZWUgbW90aGVyCm5lZSBzaXN0ZXIKbmVlIGJyb3RoZXIKbmVlIHdpZmUKbmVlIGh1c2JhbmQKZ3VkZGEgbG8KcHVrdSBsbwptb2RkYSBsbwpsYXZhZGEgbG8KYm9ra2EgbG8Kbm90bG8gcGV0dGkKZ3VkZGFsbyBwZXR0aQpwdWt1bG8gcGV0dGkKbW9kZGFsbyBwZXR0aQpkZW5ndXRhbnUKZGVuZ2VzdGEKZGVuZ2FsaQpkZW5naWNodWtvCmRlbmdleSByYQpkZW5nZXkgbGUKZGVuZ2lwb3RoYQpkZW5naXBveWEKZGVuZ2lwb3lpbmEKZGVuZ2luY2h1a3VubmEKZGVuZ2ljaHVrdW50dW5uYQpkZW5ndXR1bm5hCmRlbmd1dHVubmFudQpkZW5ndXR1bm5hdgpkZW5ndXR1bm5hZHUKZGVuZ3V0dW5uYWRpCmRlbmd1dHVubmFtCmRlbmd1dHVubmFydQpkZW5ndXR1bm5haQpkZW5nYW51CmRlbmdhdgpkZW5nYWR1CmRlbmdpbmRpCmRlbmdhbQpkZW5nYXJ1CmRlbmdhaQpkZW5naW5hCmRlbmdpbmF2CmRlbmdpbmFkdQpkZW5naW5hZGkKZGVuZ2luYW0KZGVuZ2luYXJ1CmRlbmdpbmFpCmRlbmdlc2FudQpkZW5nZXNhdgpkZW5nZXNhZHUKZGVuZ2VzYWRpCmRlbmdlc2FtCmRlbmdlc2FydQpkZW5nZXNhaQpkZW5nZXN0YXYKZGVuZ2VzdGFkdQpkZW5nZXN0YWRpCmRlbmdlc3RhbQpkZW5nZXN0YXJ1CmRlbmdlc3RhaQpkZW5ndXRhdgpkZW5ndXRhZHUKZGVuZ3V0YWRpCmRlbmd1dGFtCmRlbmd1dGFydQpkZW5ndXRhaQpwdWt1bG8gZGVuZ3V0YW51Cmd1ZGRhbG8gZGVuZ3V0YW51Cm5vdGxvIGRlbmd1dGFudQpib2trYWxvIGRlbmd1dGFudQpsYXZhZGFsbyBkZW5ndXRhbnUKbW9kZGFsbyBkZW5ndXRhbnUKcHVrdSBkZW5ndXRhbnUKZ3VkZGEgZGVuZ3V0YW51CmJva2thIGRlbmd1dGFudQpsYXZhZGEgZGVuZ3V0YW51Cm1vZGRhIGRlbmd1dGFudQpub3J1IGRlbmd1dGFudQpwdWt1IHJhCmd1ZGRhIHJhCmJva2thIHJhCmxhdmFkYSByYQptb2RkYSByYQpub3J1IHJhCnB1a3UgbGUKZ3VkZGEgbGUKYm9ra2EgbGUKbGF2YWRhIGxlCm1vZGRhIGxlCm5vcnUgbGUKcHVrdSBsYW5qYQpndWRkYSBsYW5qYQpib2trYSBsYW5qYQpsYXZhZGEgbGFuamEKbW9kZGEgbGFuamEKbm9ydSBsYW5qYQpwdWt1IGtvZGFrYQpndWRkYSBrb2Rha2EKYm9ra2Ega29kYWthCmxhdmFkYSBrb2Rha2EKbW9kZGEga29kYWthCm5vcnUga29kYWthCnB1a3UgbXVuZGEKZ3VkZGEgbXVuZGEKYm9ra2EgbXVuZGEKbGF2YWRhIG11bmRhCm1vZGRhIG11bmRhCm5vcnUgbXVuZGEKcHVrdSBkb25nYQpndWRkYSBkb25nYQpib2trYSBkb25nYQpsYXZhZGEgZG9uZ2EKbW9kZGEgZG9uZ2EKbm9ydSBkb25nYQpwdWt1IGVycmkKZ3VkZGEgZXJyaQpib2trYSBlcnJpCmxhdmFkYSBlcnJpCm1vZGRhIGVycmkKbm9ydSBlcnJpCnB1a3UgcGljY2hpCmd1ZGRhIHBpY2NoaQpib2trYSBwaWNjaGkKbGF2YWRhIHBpY2NoaQptb2RkYSBwaWNjaGkKbm9ydSBwaWNjaGkKcHVrdSB3YXN0ZQpndWRkYSB3YXN0ZQpib2trYSB3YXN0ZQpsYXZhZGEgd2FzdGUKbW9kZGEgd2FzdGUKbm9ydSB3YXN0ZQpwdWt1bG8gcGV0dGkgZGVuZ3V0YW51Cmd1ZGRhbG8gcGV0dGkgZGVuZ3V0YW51Cm5vdGxvIHBldHRpIGRlbmd1dGFudQpib2trYWxvIHBldHRpIGRlbmd1dGFudQpsYXZhZGFsbyBwZXR0aSBkZW5ndXRhbnUKbW9kZGFsbyBwZXR0aSBkZW5ndXRhbnUKeW91IGFyZSBzdHVwaWQKeW91IGFyZSBhbiBpZGlvdAp5b3UncmUgc28gZHVtYgp3aGF0IGEgbG9zZXIKaSB3aWxsIGZpbmQgeW91CnlvdSBkZXNlcnZlIHRvIGRpZQppIGhhdGUgeW91CnlvdSdyZSBkaXNndXN0aW5nCm5vYm9keSBsaWtlcyB5b3UKeW91J3JlIHBhdGhldGljCmdldCBsb3N0Cm5vYm9keSBhc2tlZAp5b3UncmUgd29ydGhsZXNzCnlvdSdyZSB0cmFzaApraWxsIHlvdXJzZWxmCnlvdSdyZSB1Z2x5CnlvdSdyZSBhbm5veWluZwpnbyB0byBoZWxsCnN0dXBpZCBnYSB1bm5hdgp0aGlzIGlzIGdhcmJhZ2UKbm9ib2R5IGFza2VkIGZvciB5b3VyIG9waW5pb24K
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971f54578b1ed3dc958689d92603d7ae095215489dd7179648a7e2ff16d3f692
3
+ size 5780
model_output/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.2,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "embedding_size": 768,
11
+ "eos_token_id": null,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.2,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "is_decoder": false,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "bert",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "problem_type": "single_label_classification",
25
+ "tie_word_embeddings": true,
26
+ "transformers_version": "5.2.0",
27
+ "type_vocab_size": 2,
28
+ "use_cache": false,
29
+ "vocab_size": 197285
30
+ }
model_output/eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_loss": 0.6901780962944031,
3
+ "eval_accuracy": 0.9364406779661016,
4
+ "eval_f1": 0.9343065693430657,
5
+ "eval_precision": 0.9667673716012085,
6
+ "eval_recall": 0.903954802259887,
7
+ "eval_runtime": 3.8999,
8
+ "eval_samples_per_second": 181.541,
9
+ "eval_steps_per_second": 3.077,
10
+ "epoch": 10.0
11
+ }
model_output/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72de3af3094c02e1ee78a81eb746bbde6072485310b7a6a8b3f7b64f4cc2d104
3
+ size 950254568
model_output/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
model_output/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": false,
6
+ "lowercase": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": false,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
model_output/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b770c014ca4b3707937d5e42dcc6477967b5fb94dbafa2b8ef409ab12f9deb71
3
+ size 5201
out.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ b8300d6 Deploy: Comment Guard API - FastAPI + MuRIL BERT
push_out.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ To https://huggingface.co/spaces/tejesh916K/comment-guard-api
2
+ b8300d6..d82a2c9 main -> main