Add new SentenceTransformer model

README.md

@@ -165,9 +165,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 1.0000, 0.3428],
-#         [1.0000, 1.0000, 0.3428],
-#         [0.3428, 0.3428, 1.0000]])
+# tensor([[0.9999, 0.9999, 0.3432],
+#         [0.9999, 0.9999, 0.3432],
+#         [0.3432, 0.3432, 1.0000]])
 ```
 
 <!--
@@ -295,6 +295,8 @@ You can finetune this model on your own dataset.
 - `num_train_epochs`: 2
 - `warmup_ratio`: 0.05
 - `bf16`: True
+- `dataloader_num_workers`: 4
+- `dataloader_prefetch_factor`: 4
 - `load_best_model_at_end`: True
 - `optim`: stable_adamw
 - `ddp_find_unused_parameters`: False
@@ -356,8 +358,8 @@ You can finetune this model on your own dataset.
 - `tpu_metrics_debug`: False
 - `debug`: []
 - `dataloader_drop_last`: False
-- `dataloader_num_workers`: 0
-- `dataloader_prefetch_factor`: None
+- `dataloader_num_workers`: 4
+- `dataloader_prefetch_factor`: 4
 - `past_index`: -1
 - `disable_tqdm`: False
 - `remove_unused_columns`: True

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "dtype": "bfloat16",
+  "dtype": "float32",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdabf672eadb1e9ac97e314980152ee1b26acd7848dde0bbc20db2add599e297
-size 45437864
+oid sha256:1a4c777cab0e4550abe5ec81f50dd4afd6bea1e3f51a0153b8a30ba425900f61
+size 90864192