bug: fixed handler.py from root repo

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": true,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "tmp/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

handler.py

@@ -0,0 +1,29 @@
+from typing import Dict, List, Any
+from transformers import pipeline
+
+import torch.nn.functional as F
+from torch import Tensor
+from transformers import AutoTokenizer, AutoModel
+
+def average_pool(last_hidden_states: Tensor,
+                 attention_mask: Tensor) -> Tensor:
+    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
+    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        self.pipeline = pipeline("feature-extraction", model=path)
+        self.tokenizer = AutoTokenizer.from_pretrained(path)
+        self.model = AutoModel.from_pretrained(path)
+
+    def __call__(self, data: Dict[str, Any]) -> List[List[int]]:
+        inputs = data.pop("inputs",data)
+
+        batch_dict = self.tokenizer(inputs, max_length=512, padding=True, truncation=True, return_tensors='pt')
+
+        outputs = self.model(**batch_dict)
+
+        embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
+        embeddings = F.normalize(embeddings, p=2, dim=1)
+        scores = (embeddings[:2] @ embeddings[2:].T) * 100
+        return scores.tolist()

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d741c1a688a6169af0ecb5a047c44645cd992c31e1bf431269f98bba9ae2911a
+size 1340616616

modules.json

@@ -0,0 +1,20 @@
+[
+    {
+      "idx": 0,
+      "name": "0",
+      "path": "",
+      "type": "sentence_transformers.models.Transformer"
+    },
+    {
+      "idx": 1,
+      "name": "1",
+      "path": "1_Pooling",
+      "type": "sentence_transformers.models.Pooling"
+    },
+    {
+      "idx": 2,
+      "name": "2",
+      "path": "2_Normalize",
+      "type": "sentence_transformers.models.Normalize"
+    }
+  ]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3fda35853349a026a61027d93bbfd65d7658287a2043f95af3e4397a4e9c5e
+size 1340698349

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}

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 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}