Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

MedEmbed-large-v0.1.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5bb0de0bcecaf2813e842d5e4ec0eefd413893bfe0ff87b60308f818c112765
+size 1350563071

README.md

@@ -0,0 +1,49 @@
+# MedEmbed-large-v0.1 ONNX Model
+
+This repository contains an ONNX version of the MedEmbed-large-v0.1 model, which was originally a SentenceTransformer model.
+
+## Model Description
+
+The original MedEmbed-large-v0.1 model is a sentence embedding model specialized for medical text. This ONNX version maintains the same functionality but is optimized for deployment in production environments.
+
+## ONNX Conversion
+
+The model was converted to ONNX format using PyTorch's `torch.onnx.export` functionality with ONNX opset version 14.
+
+## Model Inputs and Outputs
+
+- **Inputs**:
+  - `input_ids`: Tensor of shape `[batch_size, sequence_length]`
+  - `attention_mask`: Tensor of shape `[batch_size, sequence_length]`
+
+- **Output**:
+  - `sentence_embedding`: Tensor of shape `[batch_size, embedding_dimension]`
+
+## Usage with Hugging Face
+
+```python
+import onnxruntime as ort
+from transformers import AutoTokenizer
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained("YOUR_MODEL_PATH")
+
+# Load ONNX model
+onnx_path = "YOUR_MODEL_PATH/MedEmbed-large-v0.1.onnx"
+session = ort.InferenceSession(onnx_path)
+
+# Tokenize input text
+text = "Your medical text here"
+inputs = tokenizer(text, return_tensors="np", padding=True, truncation=True)
+
+# Run inference with ONNX model
+onnx_inputs = {
+    "input_ids": inputs["input_ids"],
+    "attention_mask": inputs["attention_mask"]
+}
+embeddings = session.run(None, onnx_inputs)[0]
+```
+
+## Usage with OpenSearch
+
+This model can be used with OpenSearch's neural search capabilities. Please refer to OpenSearch documentation for details on how to load and use ONNX models for text embedding.

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "medical-bge-large-mix2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.0",
+    "transformers": "4.45.2",
+    "pytorch": "2.4.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

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"
+  }
+]

sentence_bert_config.json

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

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 +1,57 @@
+{
+  "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": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}