Add new SentenceTransformer model.

README.md

@@ -12,31 +12,31 @@ tags:
 - dataset_size:200
 - loss:SoftmaxLoss
 widget:
-- source_sentence: '  AI streamlines data management systems effectively,'
+- source_sentence: '  AI significantly contributes to my research efficiency,'
   sentences:
-  - '  AI threatens the job security of call center employees,'
-  - '  AI can replicate human-like intuition in specific domains,'
-  - '  AI can replicate humorous interactions similar to humans,'
-- source_sentence: '  The future of jobs looks uncertain due to AI,'
+  - '  I feel apprehensive about AIs influence on job markets,'
+  - '  AI tools support me in delivering better results,'
+  - '  AI could reduce the need for human intervention in many fields,'
+- source_sentence: '  I feel tense dealing with advanced AI technologies,'
   sentences:
-  - '  AI systems can autonomously finetune their models,'
-  - '  AIs standard for data accuracy is commendable,'
-  - '  The complexity of AI functionalities can be daunting,'
-- source_sentence: '  AIs data cleaning quality is impressive,'
+  - '  I worry that AI will eventually replace my job,'
+  - '  AI can replicate humorous interactions similar to humans,'
+  - '  AI could lead to significant job losses in various industries,'
+- source_sentence: '  AIs adaptability to new information is remarkable,'
   sentences:
-  - '  AI adoption could lead to transformative job restructuring,'
-  - '  AI could make many existing job roles redundant,'
-  - '  The quality of AI in content generation is notable,'
-- source_sentence: '  AI improves my productivity by handling repetitive tasks,'
+  - '  The quality of AI-generated translations is impressive,'
+  - '  My reliance on AI generates occasional stress,'
+  - '  AI might affect the stability of job markets globally,'
+- source_sentence: '  The high quality of AI in voice synthesis is staggering,'
   sentences:
-  - '  I feel apprehensive about AIs future implications,'
-  - '  The spread of AI technology is a threat to job security,'
-  - '  AI adapts to varying user inputs accurately,'
-- source_sentence: '  AI effortlessly adapts to real-time user inputs,'
+  - '  AIs accuracy in identifying patterns is excellent,'
+  - '  AIs diagnostic capabilities in healthcare are impressive,'
+  - '  AI can self-optimize based on performance metrics,'
+- source_sentence: '  AI enhances my capability to manage diverse projects,'
   sentences:
-  - '  The rapid adoption of AI may lead to job insecurity,'
-  - '  AI-generated dialogue feels convincingly human,'
-  - '  I am anxious about relying on AI for critical decisions,'
+  - '  AI can mimic nuanced human interactions,'
+  - '  AI could replace numerous jobs in logistics,'
+  - '  AIs predictive analyses are consistently accurate,'
 ---
 
 # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
@@ -89,9 +89,9 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("zihoo/all-MiniLM-L6-v2-AINLI")
 # Run inference
 sentences = [
-    '  AI effortlessly adapts to real-time user inputs,',
-    '  The rapid adoption of AI may lead to job insecurity,',
-    '  I am anxious about relying on AI for critical decisions,',
+    '  AI enhances my capability to manage diverse projects,',
+    '  AI can mimic nuanced human interactions,',
+    '  AIs predictive analyses are consistently accurate,',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -154,11 +154,11 @@ You can finetune this model on your own dataset.
   | type    | string                                                                            | string                                                                            | int                                                               |
   | details | <ul><li>min: 8 tokens</li><li>mean: 11.91 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 11.91 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>0: ~12.00%</li><li>1: ~1.50%</li><li>2: ~86.50%</li></ul> |
 * Samples:
-  | sentence_0                                                              | sentence_1                                                              | label          |
-  |:------------------------------------------------------------------------|:------------------------------------------------------------------------|:---------------|
-  | <code>  AI advancements could eliminate various technical jobs,</code>  | <code>  I feel stressed about using AI in professional settings,</code> | <code>2</code> |
-  | <code>  AI systems can autonomously update their operations,</code>     | <code>  AI mimics human social behavior in digital assistants,</code>   | <code>2</code> |
-  | <code>  AI can understand and respond to emotions during a chat,</code> | <code>  The quality of AI in content generation is notable,</code>      | <code>2</code> |
+  | sentence_0                                                               | sentence_1                                                                  | label          |
+  |:-------------------------------------------------------------------------|:----------------------------------------------------------------------------|:---------------|
+  | <code>  AI can hold a relevant and coherent conversation,</code>         | <code>  The automation provided by AI could reduce job availability,</code> | <code>2</code> |
+  | <code>  The concept of AI making autonomous decisions worries me,</code> | <code>  I am hesitant to rely on AI for financial advice,</code>            | <code>0</code> |
+  | <code>  AI has the potential to displace many technical jobs,</code>     | <code>  AI improves my productivity by handling repetitive tasks,</code>    | <code>2</code> |
 * Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
 
 ### Training Hyperparameters
@@ -166,7 +166,7 @@ You can finetune this model on your own dataset.
 
 - `per_device_train_batch_size`: 64
 - `per_device_eval_batch_size`: 64
-- `num_train_epochs`: 6
+- `num_train_epochs`: 8
 - `multi_dataset_batch_sampler`: round_robin
 
 #### All Hyperparameters
@@ -188,7 +188,7 @@ You can finetune this model on your own dataset.
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1
-- `num_train_epochs`: 6
+- `num_train_epochs`: 8
 - `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1d403db5186f9ae6b4354d3597287b8f3e280a893246af9e089b797b0ab610
+oid sha256:89a766fa0b350d587f5b96b0aaa7a3e480798ffa226c9ea2dda3e947ce7f3433
 size 90864192