Upload 6 files

README.md

@@ -1,3 +1,51 @@
----
-license: apache-2.0
----
+## Usage
+
+```python
+from transformers import AutoModel, AutoTokenizer
+import torch
+from torch import nn
+
+
+class Classifier(nn.Module):
+    def __init__(self):
+        super(Classifier, self).__init__()
+        self.fc1 = nn.Linear(1024, 4096)
+        self.fc2 = nn.Linear(4096, 512)
+        self.fc3 = nn.Linear(512, 2)
+        self.dropout = nn.Dropout(p=0.1)
+        self.leaky_relu = nn.LeakyReLU(negative_slope=0.01)
+
+    def forward(self, x):
+        x = self.leaky_relu(self.fc1(x))
+        x = self.dropout(x)
+        x = self.leaky_relu(self.fc2(x))
+        x = self.dropout(x)
+        x = self.fc3(x)
+        return x
+
+
+class CombinedModel(nn.Module):
+    def __init__(self, transformer_model_name, classifier_checkpoint_path):
+        super(CombinedModel, self).__init__()
+        self.transformer = AutoModel.from_pretrained(transformer_model_name)
+        self.tokenizer = AutoTokenizer.from_pretrained(transformer_model_name)
+        self.classifier = Classifier()
+        classifier_checkpoint = torch.load(classifier_checkpoint_path, map_location=torch.device('mps')) # could set cpu, cuda
+        self.classifier.load_state_dict(classifier_checkpoint)
+
+    def forward(self, text):
+        outputs = self.tokenizer(text, return_tensors='pt', truncation=True, padding=True)
+        transformer_outputs = self.transformer(**outputs)
+        pooled_output = transformer_outputs.pooler_output
+        logits = self.classifier(pooled_output)
+        return logits
+
+
+model = CombinedModel('intfloat/multilingual-e5-large', 'path/to/best_model.pt')
+model.eval()
+
+def get_label(query, doc):
+  text = f"Запрос: {query} /Документ: {doc}"
+  logits = model(text)
+  return torch.softmax(logits, dim=1).detach().numpy()
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-large",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3368573cb1c55185395a7e157103543600e178e9d4f68d199f99a2e5b4f99a6d
+size 2264914238

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "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>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}