Upload 8 files

config.json

@@ -0,0 +1,12 @@
+{
+  "architectures": [
+    "Chimera"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_marqo_arctic_bge_chimera_m.ChimeraConfig",
+    "AutoModel": "modeling_marqo_arctic_bge_chimera_m.Chimera"
+  },
+  "model_type": "marqo-chimera-arctic-bge-m",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2"
+}

configuration_marqo_arctic_bge_chimera_m.py

@@ -0,0 +1,10 @@
+from transformers import PretrainedConfig
+import torch.nn as nn
+from typing import List, Union
+
+
+class ChimeraConfig(PretrainedConfig):
+    model_type = "marqo-chimera-arctic-bge-m"
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9185237e2a937d3a7421464a6876b4b6e44aaf849d3eb7439f1a051b436751a2
+size 871183080

modeling_marqo_arctic_bge_chimera_m.py

@@ -0,0 +1,68 @@
+import torch
+import torch.nn as nn
+from transformers import BertModel, PreTrainedModel, BertConfig, AutoModel
+from typing import List
+from .configuration_marqo_arctic_bge_chimera_m import ChimeraConfig
+
+
+class Chimera(PreTrainedModel):
+    config_class = ChimeraConfig
+
+    def __init__(self, config: ChimeraConfig):
+        super().__init__(config)
+        bert_config = BertConfig(
+            vocab_size=30522,
+            hidden_size=768,
+            num_hidden_layers=12,
+            num_attention_heads=12,
+            intermediate_size=3072,
+            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),
+            }
+        )
+
+    def forward(
+        self,
+        input_ids: torch.Tensor,
+        attention_mask: torch.Tensor,
+        token_type_ids: torch.Tensor = None,
+    ) -> torch.Tensor:
+        embeddings = []
+        for _, model in self.model.items():
+            model_output = model(
+                input_ids=input_ids,
+                attention_mask=attention_mask,
+                token_type_ids=token_type_ids,
+            )
+            pooled_output = model_output[0][:, 0]
+            embeddings.append(pooled_output)
+
+        return torch.cat(embeddings, dim=-1)
+
+    def load_weights_from_automodels(
+        self, in_models: List[str], has_pooling_layer: List[bool]
+    ):
+        model_list = []
+        for i, model_name in enumerate(in_models):
+            model = AutoModel.from_pretrained(
+                model_name,
+                add_pooling_layer=has_pooling_layer[i],
+                trust_remote_code=True,
+            )
+            model.eval()
+            model_list.append(model)
+
+        self.model = nn.ModuleDict(
+            {f"model_{i}": model for i, model in enumerate(model_list)}
+        )

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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 +1,62 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}