Copy non-ONNX

README.md

@@ -1,3 +1,3 @@
 ---
-license: unknown
+license: unlicense
 ---

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

handler.py

@@ -0,0 +1,36 @@
+from typing import Dict, List, Any
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+    
+class EndpointHandler():
+    def __init__(self, path=""):
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/msmarco-MiniLM-L-6-v3')
+        self.model = AutoModel.from_pretrained('sentence-transformers/msmarco-MiniLM-L-6-v3')
+        self.model.to(self.device)
+        print("model will run on ", self.device)
+
+    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
+        """
+       data args:
+            inputs (:obj: `str` | `PIL.Image` | `np.array`)
+            kwargs
+      Return:
+            A :obj:`list` | `dict`: will be serialized and returned
+        """
+        sentences = data.pop("inputs",data)
+        encoded_input = self.tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+        encoded_input = {key: value.to(self.device) for key, value in encoded_input.items()}
+        # Compute token embeddings
+        with torch.no_grad():
+            model_output = self.model(**encoded_input)
+
+        # Perform pooling. In this case, max pooling.
+        sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+        return sentence_embeddings.tolist()

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4593facd634592b4a1ba74db6e75b0d3a6418343a0fec6e019a07d04785b08b5
+size 128

requirements.txt

@@ -0,0 +1 @@
+torch

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 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "C:\\Users\\alvin/.cache\\huggingface\\hub\\models--sentence-transformers--all-MiniLM-L6-v2\\snapshots\\7dbbc90392e2f80f3d3c277d6e90027e55de9125\\special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1477dbc12d625e3d64d8f2f9cb5bf693eb30bccabba930eb66d06d3a3bdd84
+size 128