add model

config.json

@@ -3,8 +3,8 @@
     "PretrainedWord2VecHFModel"
   ],
   "auto_map": {
-    "AutoConfig": "pretrained_word2vec.PretrainedWord2VecHFConfig",
-    "AutoModel": "pretrained_word2vec.PretrainedWord2VecHFModel"
+    "AutoConfig": "configuration_word2vec.PretrainedWord2VecHFConfig",
+    "AutoModel": "modeling_word2vec.PretrainedWord2VecHFModel"
   },
   "hidden_size": 50,
   "model_type": "glove",

configuration_word2vec.py

@@ -0,0 +1,10 @@
+from transformers import PretrainedConfig
+
+class PretrainedWord2VecHFConfig(PretrainedConfig):
+    model_type = "glove"
+    
+    def __init__(self, num_words=400001, vector_size=50, **kwargs):
+        self.num_words = num_words
+        self.vector_size = vector_size
+        self.hidden_size = self.vector_size  # Required for sBERT
+        super().__init__(**kwargs)

modeling_word2vec.py

@@ -0,0 +1,18 @@
+from transformers import PreTrainedModel
+from torch import nn
+import torch
+from .configuration_word2vec import PretrainedWord2VecHFConfig
+
+class PretrainedWord2VecHFModel(PreTrainedModel):
+    config_class = PretrainedWord2VecHFConfig
+    
+    def __init__(self, config):
+        super().__init__(config)
+        self.embeddings = nn.Embedding(config.num_words, config.vector_size)
+        
+    def set_embeddings(self, embeddings):
+        self.embeddings = nn.Embedding.from_pretrained(torch.tensor(embeddings))
+    
+    def forward(self, input_ids, **kwargs):
+        x = self.embeddings(torch.tensor(input_ids))
+        return x