Upload 8 files

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "EIStakovskii/french_toxicity_classifier_plus_v2",
+  "architectures": [
+    "CamembertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "neutral",
+    "1": "toxic"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "neutral": 0,
+    "toxic": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfdd7aff94bdaab639326a5f6de0d79de1664b7398d1060c2d2e0891bc131a42
+size 442510176

model_script.py

@@ -0,0 +1,46 @@
+import torch
+from torch import nn
+from transformers import AutoModel
+
+class CustomModel(torch.nn.Module):
+    def __init__(self, model_path, dropout=0.1, hidden_dim=768):
+        super().__init__()
+        self.metric_names = ['valence', 'arousal']
+        self.dropout_rate = dropout
+        self.hidden_dim = hidden_dim
+
+        self.bert = AutoModel.from_pretrained(model_path)
+
+        for name in self.metric_names:
+            setattr(self, name, nn.Linear(hidden_dim, 1))
+            setattr(self, 'l_1_' + name, nn.Linear(hidden_dim, hidden_dim))
+
+        self.layer_norm = nn.LayerNorm(self.hidden_dim)
+        self.relu = nn.ReLU()
+        self.dropout = nn.Dropout(self.dropout_rate)
+        self.sigmoid = nn.Sigmoid()
+
+    def save_pretrained(self, save_directory):
+        self.bert.save_pretrained(save_directory)
+        torch.save(self.state_dict(), f'{save_directory}/pytorch_model.bin')
+
+    @classmethod
+    def from_pretrained(cls, model_dir, dropout=0.2, hidden_dim=768):
+        model = cls(model_dir, dropout, hidden_dim)
+        state_dict = torch.load(f'{model_dir}/pytorch_model.bin', map_location=torch.device('cpu'))
+        model.load_state_dict(state_dict)
+        return model
+
+    def forward(self, *args):
+        _, x = self.bert(*args, return_dict=False)
+        output = self.rate_embedding(x)
+        return output
+
+    def rate_embedding(self, x):
+        output_ratings = []
+        for name in self.metric_names:
+            first_layer = self.relu(self.dropout(self.layer_norm(getattr(self, 'l_1_' + name)(x) + x)))
+            second_layer = self.sigmoid(getattr(self, name)(first_layer))
+            output_ratings.append(second_layer)
+
+        return output_ratings

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25175f3197a5f0c5f287846d697e7e49dffd3132deb47a6062ef414b00171169
+size 447307470

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912

special_tokens_map.json

@@ -0,0 +1,55 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,78 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "CamembertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}