Add new SentenceTransformer model.

README.md

@@ -12,31 +12,31 @@ tags:
 - dataset_size:200
 - loss:SoftmaxLoss
 widget:
-- source_sentence: '  I worry that AI will eventually replace my job,'
+- source_sentence: '  AIs conversational abilities are becoming more human-like,'
   sentences:
-  - '  AI might affect the stability of job markets globally,'
-  - '  AI can mimic human facial expressions,'
-  - '  AIs flexibility in updating its models is remarkable,'
-- source_sentence: '  AIs efficiency in data mining is impressive,'
+  - '  AI-generated presentations are often high-quality,'
+  - '  AIs conversational prowess rivals that of humans,'
+  - '  I feel intimidated by the complexity of AI technologies,'
+- source_sentence: '  AI-generated presentations are often high-quality,'
   sentences:
-  - '  AI could reduce the need for human intervention in many fields,'
-  - '  AI will possibly replace customer service jobs,'
-  - '  AI systems modify their processes based on feedback,'
-- source_sentence: '  AI can adjust to user preferences over time,'
+  - '  AIs progress poses risks to current job structures,'
+  - '  I get nervous when I have to use AI for complex tasks,'
+  - '  AI could lead to significant shifts in employment trends,'
+- source_sentence: '  AIs data cleaning quality is impressive,'
   sentences:
-  - ' AI can simulate human emotions in interactions,'
-  - '  AIs precision in data analysis is highly reliable,'
-  - '  The rapid growth of AI makes me uneasy,'
-- source_sentence: '  AI tools optimize my workflow, making tasks simpler,'
+  - '  I am anxious about relying on AI for critical decisions,'
+  - '  AI could make many existing job roles redundant,'
+  - '  AI could greatly impact the future job landscape,'
+- source_sentence: '  Relying on AI for critical thinking tasks makes me nervous,'
   sentences:
-  - '  AI tools aid significantly in project execution,'
-  - '  AI can carry on meaningful conversations over the phone,'
-  - '  AI helps me make better decisions through data analysis,'
-- source_sentence: '  AI effectively enhances my problem-solving strategies,'
+  - '  The rise of AI is creating job displacement fears,'
+  - '  The rapid growth of AI makes me uneasy,'
+  - '  I hesitate to use AI-powered tools without supervision,'
+- source_sentence: '  AIs efficiency in data mining is impressive,'
   sentences:
-  - '  AI consistently provides reliable recommendations,'
-  - '  AI tools support me in delivering better results,'
-  - '  AI optimizes content strategy through data analysis,'
+  - '  AI will possibly replace customer service jobs,'
+  - '  AIs interactive capabilities feel almost human,'
+  - '  AI enhances my capability to manage diverse projects,'
 ---
 
 # 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 effectively enhances my problem-solving strategies,',
-    '  AI consistently provides reliable recommendations,',
-    '  AI optimizes content strategy through data analysis,',
+    '  AIs efficiency in data mining is impressive,',
+    '  AI will possibly replace customer service jobs,',
+    '  AI enhances my capability to manage diverse projects,',
 ]
 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: ~9.00%</li><li>1: ~69.00%</li><li>2: ~22.00%</li></ul> |
 * Samples:
-  | sentence_0                                                                      | sentence_1                                                                      | label          |
-  |:--------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:---------------|
-  | <code>  AI systems autonomously integrate user feedback for improvements</code> | <code>  AI systems autonomously integrate user feedback for improvements</code> | <code>0</code> |
-  | <code>  AI can exhibit empathy in certain contexts,</code>                      | <code>  The quality of AI in customer feedback analysis is notable,</code>      | <code>2</code> |
-  | <code>  I feel stressed about using AI in professional settings,</code>         | <code>  I feel tense dealing with advanced AI technologies,</code>              | <code>0</code> |
+  | sentence_0                                                      | sentence_1                                                         | label          |
+  |:----------------------------------------------------------------|:-------------------------------------------------------------------|:---------------|
+  | <code>  AI-generated stories feel incredibly human,</code>      | <code>  Using AI tools makes me feel anxious,</code>               | <code>2</code> |
+  | <code>  AI-generated dialogue feels convincingly human,</code>  | <code>  AI could greatly impact the future job landscape,</code>   | <code>1</code> |
+  | <code>  AI helps me manage my schedule more efficiently,</code> | <code>  AI can recognize and respond to human-like sarcasm,</code> | <code>1</code> |
 * Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
 
 ### Training Hyperparameters
@@ -166,6 +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`: 4
 - `multi_dataset_batch_sampler`: round_robin
 
 #### All Hyperparameters
@@ -187,7 +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`: 3
+- `num_train_epochs`: 4
 - `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 sha256:8d11d89d38b73dc9bbee44dd082835092283a177546e02e2ff87748ef6863ac0
+oid sha256:061e1a54c00a54ad184f6f1a8bf0a296b3b5bc09eadf099a2e9d0b298881ac67
 size 90864192