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, 0.3433],
-#         [1.0000, 1.0000, 0.3433],
-#         [0.3433, 0.3433, 1.0000]])
+# tensor([[1.0000, 1.0000, 0.3655],
+#         [1.0000, 1.0000, 0.3655],
+#         [0.3655, 0.3655, 1.0000]])
 ```
 
 <!--
@@ -288,7 +288,6 @@ You can finetune this model on your own dataset.
 - `eval_strategy`: steps
 - `per_device_train_batch_size`: 1152
 - `per_device_eval_batch_size`: 1152
-- `gradient_accumulation_steps`: 2
 - `weight_decay`: 0.001
 - `adam_beta2`: 0.98
 - `adam_epsilon`: 1e-06
@@ -316,7 +315,7 @@ You can finetune this model on your own dataset.
 - `per_device_eval_batch_size`: 1152
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
-- `gradient_accumulation_steps`: 2
+- `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
 - `learning_rate`: 5e-05

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 sha256:8aa70c5a8c7f662f3c19176fc258b7ec3880da54fdf54f99cdf12236f5d5bc06
-size 45437864
+oid sha256:41ddaf37362229cd67dce6f7afa240ab7dfba4b1462c9571d8e6e5d6ebed73eb
+size 90864192