Upload using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+library_name: light-embed
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
+---
+
+# onnx-models/paraphrase-albert-small-v2-onnx
+
+This is the ONNX-ported version of the [sentence-transformers/paraphrase-albert-small-v2](https://huggingface.co/sentence-transformers/paraphrase-albert-small-v2) for generating text embeddings.
+
+## Model details
+- Embedding dimension: 768
+- Max sequence length: 100
+- File size on disk:  0.04 GB
+- Modules incorporated in the onnx: Transformer, Pooling
+
+<!--- Describe your model here -->
+
+## Usage
+
+Using this model becomes easy when you have [light-embed](https://pypi.org/project/light-embed/) installed:
+
+```
+pip install -U light-embed
+```
+
+Then you can use the model by specifying the *original model name* like this:
+
+```python
+from light_embed import TextEmbedding
+sentences = [
+	"This is an example sentence",
+	"Each sentence is converted"
+]
+
+model = TextEmbedding('sentence-transformers/paraphrase-albert-small-v2')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+or by specifying the *onnx model name* like this:
+
+```python
+from light_embed import TextEmbedding
+sentences = [
+	"This is an example sentence",
+	"Each sentence is converted"
+]
+
+model = TextEmbedding('onnx-models/paraphrase-albert-small-v2-onnx')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## Citing & Authors
+
+Binh Nguyen / [email protected]

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-albert-small-v2",
+  "architectures": [
+    "AlbertModel"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 6,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.7.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9789755b432db7e44f02f56b22057cb607baf22d436310296eb67ee50d95aa58
+size 44608282

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "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 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "max_length": 100,
+  "model_max_length": 100,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "tokenizer_class": "AlbertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}