Add tokenizer files

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b69ab086c28bf90466ed1c89ba48599df0bc9fac7d7a4b32803cadc73f6fa15
+oid sha256:6c540362d99c431f4db180455419fb894da3f8329b2ed60c1d3b405e74693130
 size 571419272

modeling_arctic_m_bge_small.py

@@ -18,7 +18,7 @@ class ConcatModel(PreTrainedModel):
 
     def __init__(self, config: ConcatModelConfig):
         super().__init__(config)
-        bert_config = BertConfig(
+        bert_config_1 = BertConfig(
             vocab_size=30522,
             hidden_size=768,
             num_hidden_layers=12,
@@ -33,10 +33,25 @@ class ConcatModel(PreTrainedModel):
             layer_norm_eps=1e-12,
         )
 
+        bert_config_2 = BertConfig(
+            vocab_size=30522,
+            hidden_size=384,
+            num_hidden_layers=12,
+            num_attention_heads=12,
+            intermediate_size=1536,
+            hidden_act="gelu",
+            hidden_dropout_prob=0.1,
+            attention_probs_dropout_prob=0.1,
+            max_position_embeddings=512,
+            type_vocab_size=2,
+            initializer_range=0.02,
+            layer_norm_eps=1e-12,
+        )
+
         self.model = nn.ModuleDict(
             {
-                "model_0": BertModel(bert_config),
-                "model_1": BertModel(bert_config),
+                "model_0": BertModel(bert_config_1),
+                "model_1": BertModel(bert_config_2),
             }
         )
 
@@ -45,6 +60,7 @@ class ConcatModel(PreTrainedModel):
         input_ids: torch.Tensor,
         attention_mask: torch.Tensor,
         token_type_ids: torch.Tensor = None,
+        **kwargs
     ) -> torch.Tensor:
         embeddings = []
         for _, model in self.model.items():

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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,
+  "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]"
+}