Initial upload of models and data from GCP VM

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.csv filter=lfs diff=lfs merge=lfs -text

jigsaw_test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36700132818c49c0d97317c1541bfc97edc031175faf225db1800ec4f88a6e81
+size 25428942

jigsaw_train.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca631c01abc956d0dea7fc8c7c304900aa240abba982ac8f959f11cccf0893a
+size 51747035

jigsaw_val.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4630124deb160542835d27d088c6153638bf6322644403dd1b1b387776d1fa14
+size 12816770

merged_moderation_dataset.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbb63a3e70e350b53c01a8a6f8b166c22e5e514eca647f7a4c83234f1ec66a7
+size 64923877

merged_test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fd150f32d68e198941e3ea39ed784fd53ecc199eb3fd8dae0f4d932011e5e8
+size 25466483

merged_train.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c6f63f5a42521489cf73fd3de71a3733a9e0ebbd758f73cd1dd3034c65cace
+size 51867687

merged_val.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c673d0484479acd13d4f7b0c2e8c15eaadec8b13f0f8852ba25e86e5bb574ee
+size 12857193

ml_moderation_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f117b3705af6a5d07ae449b3292b85c7faff43a5f43d1182afc59f36f3920446
+size 5201460

test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2513ce4abb98c4d1d216e3ca0d4377d57589a0989aa8c06a840509a16c786e8
+size 60354593

test_labels.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a56dcbeba5c05f965a636f56cb5ae972bad60c3b952c239b49be18d7ab70f49
+size 4976930

tinyBert_moderation_model_run2/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1200,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pre_trained": "",
+  "problem_type": "single_label_classification",
+  "structure": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

tinyBert_moderation_model_run2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcad514b2f33ace0055858f656e9e8f7531cfac094ef51c530d21a8efca64e90
+size 57413060

tinyBert_moderation_model_run2/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tinyBert_moderation_model_run2/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4084611bd27c939ba98e5e63bc3e5a2c1a4e99477dcba46c829e4c986c429d
+size 68802655

youtube_spam_combined.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef67cffaa5119dc54b03e96535e5a5a904a668eff28f2bbe8dbf88d7aca371bc
+size 198627

youtube_test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a011d147d231097c2ed43b559d21da4c9130ce5386667621d03a78cfcbdecb
+size 37552

youtube_train.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:643118e6eab398514338623f0aba13e1fb6eb7a8eaf9b37838313fe6590efd54
+size 120663

youtube_val.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6112aa04dc2ac874ad9ddf84f86755c3c18fa4f83ff1bf7cee19bb3d1dcc48
+size 40434