Upload 25 files

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+ "word_embedding_dimension": 1024,
+ "pooling_mode_cls_token": false,
+ "pooling_mode_mean_tokens": true,
+ "pooling_mode_max_tokens": false,
+ "pooling_mode_mean_sqrt_len_tokens": false
+}

2_Dense/config.json

@@ -0,0 +1,6 @@
+{
+ "in_features": 1024,
+ "out_features": 4096,
+ "bias": true,
+ "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8011cb0638bcd225e7bd0b391e9f7d595dedb801c42f9c8dc36463f0b1b39d7
+size 16795132

2_Dense_1024/config.json

@@ -0,0 +1,6 @@
+{
+ "in_features": 1024,
+ "out_features": 1024,
+ "bias": true,
+ "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense_1024/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39c1d3b787212240a1c2a20833ce4a2107e84bf56a3c68df924250c735697e1
+size 4199932

2_Dense_1536/config.json

@@ -0,0 +1,6 @@
+{
+ "in_features": 1024,
+ "out_features": 1536,
+ "bias": true,
+ "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense_1536/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b65c97b6553c42428e0ffc2066725a2436cd676ff956886c5857d5f5c7e829
+size 6299132

2_Dense_1792/config.json

@@ -0,0 +1,6 @@
+{
+ "in_features": 1024,
+ "out_features": 1792,
+ "bias": true,
+ "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense_1792/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ffab47ef95714827aba550f49fbd11919572eff02f4313f9e3564ebd839ec9e
+size 7348732

2_Dense_2048/config.json

@@ -0,0 +1,6 @@
+{
+ "in_features": 1024,
+ "out_features": 2048,
+ "bias": true,
+ "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense_2048/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eef68978561189b35651a7035e177d58b79c1c9e843efe2ce9a3f511d42f625
+size 8398332

2_Dense_256/config.json

@@ -0,0 +1,6 @@
+{
+ "in_features": 1024,
+ "out_features": 256,
+ "bias": true,
+ "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense_256/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5f629d5ecb9866b0903dc52363ac0771741673dbfe109c8684d52c678362e0
+size 1051132

2_Dense_4096/config.json

@@ -0,0 +1,6 @@
+{
+ "in_features": 1024,
+ "out_features": 4096,
+ "bias": true,
+ "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense_4096/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8011cb0638bcd225e7bd0b391e9f7d595dedb801c42f9c8dc36463f0b1b39d7
+size 16795132

2_Dense_768/config.json

@@ -0,0 +1,6 @@
+{
+ "in_features": 1024,
+ "out_features": 768,
+ "bias": true,
+ "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense_768/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b70dcfda0413991abf475fc44f6b146c49064d106065701ea23f85b64f4a251
+size 3150332

README.md

@@ -0,0 +1,60 @@
+
+# 模型介绍
+
+主要针对检索和语义匹配任务，本人实测要好于当前大多数向量模型。
+
+支持多个向量维度：256，768，1024，1563，1792，2048，4096
+
+支持中英互搜，但是英文表征能力要弱于中文
+
+# 模型目录结构
+
+结构很简单，就是标准的SentenceTransformer文件目录 + 一系列`2_Dense_{dims}`文件夹，dims代表最终的向量维度。
+
+举个例子，`2_Dense_256`文件夹里存储了把向量维度转换为256维的Linear权重，具体如何使用请看下面的章节
+
+# 模型使用方法
+
+可直接用SentenceTransformer加载，也可以使用transformer加载使用：
+
+```python
+import os
+import torch
+from transformers import AutoModel, AutoTokenizer
+from sentence_transformers import SentenceTransformer
+from sklearn.preprocessing import normalize
+
+# 待编码文本
+texts = ["通用向量编码", "hello world", "支持中英互搜，不建议纯英文场景使用"]
+# 模型目录
+model_dir = "{MODEL_PATH}"
+
+#### 方法1：使用SentenceTransformer
+# ！！！！！！！！！！！！！！默认是4096维度，如需其他维度，请自行复制2_Dense_{dims}中的文件到2_Dense文件夹中覆盖！！！！！！！！！！！！！！
+model = SentenceTransformer(model_dir)
+vectors = model.encode(texts, convert_to_numpy=True, normalize_embeddings=True)
+print(vectors.shape)
+print(vectors[:, :4])
+
+#### 方法2：使用transformers库
+# ！！！！！！！！！！！！！！ 本代码会根据vector_dim值会读取对应的Linear层权重，请按需选择vector_dim ！！！！！！！！！！！！！！
+vector_dim = 4096
+model = AutoModel.from_pretrained(model_dir).eval()
+tokenizer = AutoTokenizer.from_pretrained(model_dir)
+vector_linear = torch.nn.Linear(in_features=model.config.hidden_size, out_features=vector_dim)
+vector_linear_dict = {
+    k.replace("linear.", ""): v for k, v in
+    torch.load(os.path.join(model_dir, f"2_Dense_{vector_dim}/pytorch_model.bin")).items()
+}
+vector_linear.load_state_dict(vector_linear_dict)
+with torch.no_grad():
+    input_data = tokenizer(texts, padding="longest", truncation=True, max_length=512, return_tensors="pt")
+    attention_mask = input_data["attention_mask"]
+    last_hidden_state = model(**input_data)[0]
+    last_hidden = last_hidden_state.masked_fill(~attention_mask[..., None].bool(), 0.0)
+    vectors = last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
+    vectors = normalize(vector_linear(vectors).cpu().numpy())
+print(vectors.shape)
+print(vectors[:, :4])
+
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

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_Dense",
+  "type": "sentence_transformers.models.Dense"
+ }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30cd755f63be9334d2dfef6d643908b49853a0e723e897c4eb31d4ff111fd8ec
+size 2472524610

sentence_bert_config.json

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

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "</s>",
+    "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 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}