Duplicate from onnx-community/all-MiniLM-L6-v2-ONNX

Co-authored-by: Joshua <Xenova@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,39 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- sentence-transformers/all-MiniLM-L6-v2
+pipeline_tag: sentence-similarity
+library_name: transformers.js
+datasets:
+  - s2orc
+  - flax-sentence-embeddings/stackexchange_xml
+  - ms_marco
+  - gooaq
+  - yahoo_answers_topics
+  - code_search_net
+  - search_qa
+  - eli5
+  - snli
+  - multi_nli
+  - wikihow
+  - natural_questions
+  - trivia_qa
+  - embedding-data/sentence-compression
+  - embedding-data/flickr30k-captions
+  - embedding-data/altlex
+  - embedding-data/simple-wiki
+  - embedding-data/QQP
+  - embedding-data/SPECTER
+  - embedding-data/PAQ_pairs
+  - embedding-data/WikiAnswers
+tags:
+- feature-extraction
+---
+
+https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 with ONNX weights to be compatible with Transformers.js.
+
+## Usage (Transformers.js)
+
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
+```bash
+npm i @huggingface/transformers
+```
+
+You can then use the model to compute embeddings like this:
+
+```js
+import { pipeline } from '@huggingface/transformers';
+
+// Create a feature-extraction pipeline
+const extractor = await pipeline('feature-extraction', 'onnx-community/all-MiniLM-L6-v2-ONNX');
+
+// Compute sentence embeddings
+const sentences = ['This is an example sentence', 'Each sentence is converted'];
+const output = await extractor(sentences, { pooling: 'mean', normalize: true });
+console.log(output);
+// Tensor {
+//   dims: [ 2, 384 ],
+//   type: 'float32',
+//   data: Float32Array(768) [ 0.04592696577310562, 0.07328180968761444, ... ],
+//   size: 768
+// }
+```
+
+You can convert this Tensor to a nested JavaScript array using `.tolist()`:
+```js
+console.log(output.tolist());
+// [
+//   [ 0.04592696577310562, 0.07328180968761444, 0.05400655046105385, ... ],
+//   [ 0.08188057690858841, 0.10760223120450974, -0.013241755776107311, ... ]
+// ]
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "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",
+  "transformers_version": "4.54.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522,
+  "transformers.js_config": {
+    "dtype": "fp32",
+    "use_external_data_format": {
+      "model.onnx": 1,
+      "model_fp16.onnx": 1,
+      "model_q4.onnx": 1,
+      "model_q4f16.onnx": 1
+    }
+  }
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f019cf6217537cc4bfc7f5192f21dea1e18445177edaab0bc6163a813e5c7a1
+size 56796

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c758432aa596c30a122942dfe594c457d4d713f890926f1c5f920bd496c8de
+size 90261504

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf4044cd8469cdb93c19f42c5c547fdd8bd4c50409145ba75ed1f80cf3f5e5e
+size 96443

onnx/model_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68486e80f360c88c72cdcc555a60bec94bc74fdf69ba4140dac8c15fcff661f7
+size 45087744

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4dcb918111189b7686147e309379832fce83d4ecbf17c395961749b5788c786
+size 69663

onnx/model_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56fb7a55115e900196115a74e399beb45c2f41ae00b99525d46fb52935c4ee2a
+size 54429696

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6297f8bb2f10987bad6f36d06022bb4b4ff5289247654843d599389630fd53dd
+size 109149

onnx/model_q4f16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37a0ad962e125f02213afef98d52a606331a1c95a56c6e01d320fefb83892a2
+size 29826048

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 +1,65 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "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]"
+}