Duplicate from Xenova/bge-large-en-v1.5

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

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,79 @@
+---
+base_model: BAAI/bge-large-en-v1.5
+library_name: transformers.js
+---
+
+https://huggingface.co/BAAI/bge-large-en-v1.5 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, as follows:
+
+```js
+import { pipeline } from '@huggingface/transformers';
+
+// Create a feature-extraction pipeline
+const extractor = await pipeline('feature-extraction', 'Xenova/bge-large-en-v1.5');
+
+// Compute sentence embeddings
+const texts = [ 'Hello world.', 'Example sentence.'];
+const embeddings = await extractor(texts, { pooling: 'mean', normalize: true });
+console.log(embeddings);
+// Tensor {
+//   dims: [ 2, 1024 ],
+//   type: 'float32',
+//   data: Float32Array(2048) [ 0.03169844672083855,  0.011085662990808487, ... ],
+//   size: 2048
+// }
+
+console.log(embeddings.tolist()); // Convert embeddings to a JavaScript list
+// [
+//   [ 0.03169844672083855, 0.011085662990808487, 0.030054178088903427, ... ],
+//   [ 0.009418969973921776, -0.024539148434996605, 0.036459196358919144, ... ]
+// ]
+```
+
+You can also use the model for retrieval. For example:
+```js
+import { pipeline, cos_sim } from '@huggingface/transformers';
+
+// Create a feature-extraction pipeline
+const extractor = await pipeline('feature-extraction', 'Xenova/bge-large-en-v1.5');
+
+// List of documents you want to embed
+const texts = [
+    'Hello world.',
+    'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.',
+    'I love pandas so much!',
+];
+
+// Compute sentence embeddings
+const embeddings = await extractor(texts, { pooling: 'mean', normalize: true });
+
+// Prepend recommended query instruction for retrieval.
+const query_prefix = 'Represent this sentence for searching relevant passages: '
+const query = query_prefix + 'What is a panda?';
+const query_embeddings = await extractor(query, { pooling: 'mean', normalize: true });
+
+// Sort by cosine similarity score
+const scores = embeddings.tolist().map(
+    (embedding, i) => ({
+        id: i,
+        score: cos_sim(query_embeddings.data, embedding),
+        text: texts[i],
+    })
+).sort((a, b) => b.score - a.score);
+console.log(scores);
+// [
+//   { id: 1, score: 0.7671812872502833, text: 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.' },
+//   { id: 2, score: 0.7219157959783322, text: 'I love pandas so much!' },
+//   { id: 0, score: 0.5109676329796601, text: 'Hello world.' }
+// ]
+```
+
+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 +1,31 @@
+{
+  "_name_or_path": "BAAI/bge-large-en-v1.5",
+  "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",
+  "transformers_version": "4.34.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ed3f810d3b6d13f70dff9ca89966f39c0a0e877fb88211be7bcc070df2a2ce
+size 1336854281

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e16945f0836be1dda5d4e389357958723bf4e9e2767ecead8f4642e24f29ad
+size 298852121

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58b55f33f28b1d3038b63d1595ca86686eed3f859a4ef5222ca995ec880cede6
+size 668828771

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81862c1d889c334792a0e71b9d7eb6687a623acadfc81875c9590141996abf0d
+size 335783481

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c8860b34a399faf5b7d22002bd2b9b7eba491c53c00346e58c5ec474ec747a
+size 317725313

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddc538002dbc8c4eafdfa83b907bb66f1aa02d3348b151d819abd8284c75ff8
+size 234646267

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4842b56e233be1cc74770f57f63b1ebb6cf357cca3dd73fcdec35c019f8a5d6e
+size 336983162

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62af89b4d530ff25a1769e7290e32b7e1edb229b0077c0530fc28d2dc2446c12
+size 335783546

quantize_config.json

@@ -0,0 +1,30 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "MatMul",
+                "Mul",
+                "Softmax",
+                "Div",
+                "Shape",
+                "Erf",
+                "Reshape",
+                "Add",
+                "Unsqueeze",
+                "Gather",
+                "Constant",
+                "Slice",
+                "Concat",
+                "ReduceMean",
+                "Cast",
+                "Sub",
+                "Sqrt",
+                "Pow",
+                "Transpose"
+            ],
+            "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": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}