Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps
 ### Model Description
 - **Model Type:** Sentence Transformer
 <!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
-- **Maximum Sequence Length:** 8192 tokens
+- **Maximum Sequence Length:** 512 tokens
 - **Output Dimensionality:** 1024 tokens
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
@@ -33,7 +33,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
   (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
   (2): Normalize()
 )

config.json

@@ -1,28 +1,32 @@
 {
-  "_name_or_path": "/root/FlagEmbedding/model/checkpoint-1000",
+  "_name_or_path": "/root/FlagEmbedding/model-bgev1.5/checkpoint-23000",
   "architectures": [
-    "XLMRobertaModel"
+    "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "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,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 8194,
-  "model_type": "xlm-roberta",
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
-  "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.45.2",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc084f415a8143e0ed902b0fa5a31a46580f31595ac921772f16283c257d9b1
-size 2271064456
+oid sha256:81e697873f49662080881e6c0e7e80b7abea63c74ce4b3db9e30194f1a873afa
+size 1340612432

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daaf08a5921c5d8904a82f8567d6fe7978bfb5d781f39e00a89fcf860be09a81
-size 4533972233
+oid sha256:fa1a64e8b995e00f6e411b75879b340303eb00b5f230bfb8bdf75b680c19bcb7
+size 2673063841

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5b801ae866328c0fc70d4ceee606053130a7c2c233d3fcbf60cb4cdc20feb8f
-size 14308
+oid sha256:89b4d66b12a9e3d52e17def6a4231b687cb321618733fbde7a99deb1cc865439
+size 14180

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b0a3e7fcb2190532bf3ec1d72999db0e0b9b355630fba59249e99dd669c6408
+oid sha256:e5b103cbe52dc66168d24ab9e24c1d9c68d3dcc21bce6f6378a60df0b19b70e6
 size 1064

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 8192,
+  "max_seq_length": 512,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,48 +1,34 @@
 {
-  "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>",
+    "content": "[CLS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
+    "content": "[MASK]",
+    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "</s>",
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b74659c780d49afad7a7b9799868f75cbd3014fb6c34956e85a793028d38094a
-size 17098251
+oid sha256:d241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66
+size 711396

tokenizer_config.json

@@ -1,55 +1,57 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
       "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>"
+  "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]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f491e3b3d534472aa9bd4d8770f4a67c73de86804b7385ee37f5ad2c607beb
+oid sha256:7a6fe29199371fd81fd2708431a5a52f819558e909b52de9a507456164e8da32
 size 5432