Upload folder using huggingface_hub

README.md

@@ -0,0 +1,30 @@
+---
+base_model: jinaai/jina-embeddings-v2-small-en
+library_name: transformers.js
+pipeline_tag: feature-extraction
+---
+
+https://huggingface.co/jinaai/jina-embeddings-v2-small-en with ONNX weights to be compatible with Transformers.js.
+
+## Usage with 🤗 Transformers.js
+
+```js
+// npm i @xenova/transformers
+import { pipeline, cos_sim } from '@xenova/transformers';
+
+// Create feature extraction pipeline
+const extractor = await pipeline('feature-extraction', 'Xenova/jina-embeddings-v2-small-en',
+    { quantized: false } // Comment out this line to use the quantized version
+);
+
+// Generate embeddings
+const output = await extractor(
+    ['How is the weather today?', 'What is the current weather like today?'],
+    { pooling: 'mean' }
+);
+
+// Compute cosine similarity
+console.log(cos_sim(output[0].data, output[1].data));  // 0.9399812684139274 (unquantized) vs. 0.9341121503699659 (quantized)
+```
+
+Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "jinaai/jina-embeddings-v2-small-en",
+  "architectures": [
+    "JinaBertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "jinaai/jina-bert-implementation--configuration_bert.JinaBertConfig",
+    "AutoModel": "jinaai/jina-bert-implementation--modeling_bert.JinaBertModel",
+    "AutoModelForMaskedLM": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForMaskedLM",
+    "AutoModelForSequenceClassification": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForSequenceClassification"
+  },
+  "classifier_dropout": null,
+  "emb_pooler": "mean",
+  "feed_forward_type": "geglu",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 8192,
+  "model_max_length": 8192,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "alibi",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30528
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8daf59cab0f24c7e0231a1e3ff9c348a97f6662e9a763dd4f15d2ca2f1614e05
+size 129799236

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a90449a40a0713a76bc4cbd05742dcf8381e45e781494f133fd79f328dad1d8
+size 64973466

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70eff78f8bf60e10edfeab16a87eaf63a7e4f658aea21b456097224427c0caef
+size 32765276

quantize_config.json

@@ -0,0 +1,30 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Mul",
+                "ReduceMean",
+                "Unsqueeze",
+                "MatMul",
+                "Gather",
+                "Concat",
+                "Add",
+                "Transpose",
+                "Softmax",
+                "Sqrt",
+                "Pow",
+                "Constant",
+                "Sub",
+                "Div",
+                "Cast",
+                "Reshape",
+                "Erf",
+                "Identity",
+                "Shape"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

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 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 8192,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}