Add SetFit model

README.md

@@ -11,15 +11,15 @@ tags:
 widget:
 - text: Point out any dull descriptions that need more color
 - text: Find places where I repeat my main points unnecessarily
-- text: What's a compelling method to reveal a secret in my plot
 - text: How do I handle flashbacks in a non-linear story
-- text: Suggest some comedic elements to lighten a dark plot
+- text: How can I develop a powerful bond between my characters
+- text: Any suggestions for a surprising end to a short story
 inference: true
 ---
 
 # SetFit
 
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A LinearDiscriminantAnalysis instance is used for classification.
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
 
 The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -31,8 +31,8 @@ The model has been trained using an efficient few-shot learning technique that i
 ### Model Description
 - **Model Type:** SetFit
 <!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
-- **Classification head:** a LinearDiscriminantAnalysis instance
-- **Maximum Sequence Length:** 128 tokens
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **Maximum Sequence Length:** 512 tokens
 - **Number of Classes:** 3 classes
 <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 <!-- - **Language:** Unknown -->
@@ -101,13 +101,13 @@ preds = model("How do I handle flashbacks in a non-linear story")
 ### Training Set Metrics
 | Training set | Min | Median | Max |
 |:-------------|:----|:-------|:----|
-| Word count   | 1   | 8.7947 | 14  |
+| Word count   | 1   | 8.9171 | 15  |
 
 | Label                       | Training Sample Count |
 |:----------------------------|:----------------------|
-| chat_assistance             | 153                   |
-| comments_assistance         | 144                   |
-| pro_subscription_assistance | 117                   |
+| chat_assistance             | 163                   |
+| comments_assistance         | 150                   |
+| pro_subscription_assistance | 121                   |
 
 ### Framework Versions
 - Python: 3.10.15

config.json

@@ -1,11 +1,10 @@
 {
-  "_name_or_path": "sentence-transformers/all-MiniLM-L12-v2",
+  "_name_or_path": "thenlper/gte-small",
   "architectures": [
     "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 384,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ed5a30285dd435b59979b997f7d1c337486ad0b53d3ac0bfc78d779368452e
+oid sha256:772487fa98b86cf51ec61e86b82e441b7ffe27b2a62179dae487bba07da68c76
 size 133462128

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fb79348a3f4f81d10f2edc336d54f608748484e4225e893bde16ace5cf7280b
-size 1194755
+oid sha256:4cc523bdeea28859416f375a12072d670d6d44e47e038f94d6c18a32f1fd99ab
+size 10415

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 128,
+  "max_seq_length": 512,
   "do_lower_case": false
 }

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
+    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -41,14 +41,14 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "max_length": 128,
-  "model_max_length": 128,
+  "model_max_length": 512,
   "never_split": null,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",