Upload folder using huggingface_hub

2_Dense/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a24e740662ddf8ec666af2558717744596d1fe23fdb76beca28210e9048038
+oid sha256:343f53d79815d1296ed1b563314badea919b8e9eaac97f1cda7df6d563da61fa
 size 2364028

README.md

@@ -5,12 +5,10 @@ tags:
 - sentence-transformers
 - feature-extraction
 - sentence-similarity
-license: apache-2.0
-datasets:
-- Lynxpda/wiki-bt-veps-russian
+
 ---
 
-# LaBSE-veps
+# {MODEL_NAME}
 
 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
@@ -49,7 +47,7 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 8158 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 334 with parameters:
 ```
 {'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
@@ -64,7 +62,7 @@ The model was trained with the parameters:
 Parameters of the fit()-Method:
 ```
 {
-    "epochs": 1,
+    "epochs": 5,
     "evaluation_steps": 100,
     "evaluator": "__main__.ChainScoreEvaluator",
     "max_grad_norm": 1,
@@ -74,7 +72,7 @@ Parameters of the fit()-Method:
     },
     "scheduler": "warmupcosine",
     "steps_per_epoch": null,
-    "warmup_steps": 1000,
+    "warmup_steps": 500,
     "weight_decay": 0.01
 }
 ```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "sentence-transformers/LaBSE",
+  "_name_or_path": "Lynxpda/LaBSE-veps",
   "architectures": [
     "BertModel"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4519c9e5844fb9ebe636bc96ba56d83bb8f178a93d38fe0cdb2b47380b49a6
+oid sha256:abba0b3a86565dc1f2ac9763e3fb4da6762ae12dbc675a81dd810ea0df47866c
 size 1883730160

tokenizer_config.json

@@ -47,12 +47,19 @@
   "do_lower_case": false,
   "full_tokenizer_file": null,
   "mask_token": "[MASK]",
+  "max_length": 256,
   "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]"
 }