Add SetFit model

1_Pooling/config.json

@@ -1,10 +1,10 @@
 {
-    "word_embedding_dimension": 768,
-    "pooling_mode_cls_token": false,
-    "pooling_mode_mean_tokens": true,
-    "pooling_mode_max_tokens": false,
-    "pooling_mode_mean_sqrt_len_tokens": false,
-    "pooling_mode_weightedmean_tokens": false,
-    "pooling_mode_lasttoken": false,
-    "include_prompt": true
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
 }

README.md

@@ -16,8 +16,6 @@ metrics:
 pipeline_tag: text-classification
 library_name: setfit
 inference: true
-datasets:
-- SetFit/SentEval-CR
 base_model: sentence-transformers/paraphrase-mpnet-base-v2
 model-index:
 - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
@@ -26,18 +24,18 @@ model-index:
       type: text-classification
       name: Text Classification
     dataset:
-      name: SetFit/SentEval-CR
-      type: SetFit/SentEval-CR
+      name: Unknown
+      type: unknown
       split: test
     metrics:
     - type: accuracy
-      value: 0.8645418326693227
+      value: 0.8804780876494024
       name: Accuracy
 ---
 
 # SetFit with sentence-transformers/paraphrase-mpnet-base-v2
 
-This is a [SetFit](https://github.com/huggingface/setfit) model trained on the [SetFit/SentEval-CR](https://huggingface.co/datasets/SetFit/SentEval-CR) dataset that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. 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:
 
@@ -52,7 +50,7 @@ The model has been trained using an efficient few-shot learning technique that i
 - **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:** 2 classes
-- **Training Dataset:** [SetFit/SentEval-CR](https://huggingface.co/datasets/SetFit/SentEval-CR)
+<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 <!-- - **Language:** Unknown -->
 <!-- - **License:** Unknown -->
 
@@ -73,7 +71,7 @@ The model has been trained using an efficient few-shot learning technique that i
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.8645   |
+| **all** | 0.8805   |
 
 ## Uses
 
@@ -91,7 +89,7 @@ Then you can load this model and run inference.
 from setfit import SetFitModel
 
 # Download from the 🤗 Hub
-model = SetFitModel.from_pretrained("rajistics/setfit-model")
+model = SetFitModel.from_pretrained("josecar24/Setfit_test")
 # Run inference
 preds = model("great phone . . .")
 ```
@@ -137,7 +135,7 @@ preds = model("great phone . . .")
 - num_epochs: (1, 1)
 - max_steps: -1
 - sampling_strategy: oversampling
-- num_iterations: 20
+- num_iterations: 60
 - body_learning_rate: (2e-05, 2e-05)
 - head_learning_rate: 2e-05
 - loss: CosineSimilarityLoss
@@ -152,18 +150,20 @@ preds = model("great phone . . .")
 - load_best_model_at_end: False
 
 ### Training Results
-| Epoch | Step | Training Loss | Validation Loss |
-|:-----:|:----:|:-------------:|:---------------:|
-| 0.025 | 1    | 0.3257        | -               |
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.0083 | 1    | 0.4167        | -               |
+| 0.4167 | 50   | 0.0621        | -               |
+| 0.8333 | 100  | 0.0007        | -               |
 
 ### Framework Versions
-- Python: 3.12.12
+- Python: 3.12.3
 - SetFit: 1.1.3
-- Sentence Transformers: 5.2.0
-- Transformers: 4.57.3
-- PyTorch: 2.9.0+cpu
-- Datasets: 4.0.0
-- Tokenizers: 0.22.1
+- Sentence Transformers: 3.4.1
+- Transformers: 4.50.2
+- PyTorch: 2.6.0+cpu
+- Datasets: 3.5.0
+- Tokenizers: 0.21.0
 
 ## Citation
 

config.json

@@ -4,7 +4,6 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
-  "dtype": "float32",
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -18,6 +17,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "relative_attention_num_buckets": 32,
-  "transformers_version": "4.57.3",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.2",
   "vocab_size": 30527
 }

config_sentence_transformers.json

@@ -1,14 +1,10 @@
 {
   "__version__": {
-    "sentence_transformers": "5.2.0",
-    "transformers": "4.57.3",
-    "pytorch": "2.9.0+cpu"
-  },
-  "model_type": "SentenceTransformer",
-  "prompts": {
-    "query": "",
-    "document": ""
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.50.2",
+    "pytorch": "2.6.0+cpu"
   },
+  "prompts": {},
   "default_prompt_name": null,
   "similarity_fn_name": "cosine"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589f6a91eec40bf75e3ac4fe5a2b5120e980399315eeb716e931b9ebbfdc753f
+oid sha256:336091ddfb3dbe9654b86cb6ef12e75aa0ac0ea1dcb2824dd551543f13cde4d2
 size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080ea93dd128a9464d2e68793f4832bffde3a610a2b9a0f583d22b98e699db71
-size 7007
+oid sha256:fb4f614b4c244f1fa63b5d70752db10c4f671ed0b15409824d9ad3c7309e7a01
+size 7059

sentence_bert_config.json

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