Add SetFit model

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 768,
+  "word_embedding_dimension": 384,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

README.md

@@ -5,14 +5,11 @@ tags:
 - sentence-transformers
 - text-classification
 - generated_from_setfit_trainer
-base_model: sentence-transformers/distiluse-base-multilingual-cased-v2
+base_model: sentence-transformers/all-MiniLM-L6-v2
 metrics:
 - accuracy
 widget:
-- text: explain in detail what is FFT and the complexity of it
-- text: The p success of karger min cut after k steps
-- text: Giải thích sự khác biệt giữa mô hình học có giám sát và không giám sát. Cung
-    cấp ví dụ cho từng loại. (ít nhất 150 từ)
+- text: What are the benefits of using cloud storage?
 - text: 'Which of the following is a Code-Based Test Coverage Metrics(E. F. Miller,
     1977 dissertation)?
 
@@ -37,11 +34,21 @@ widget:
     d.
 
     C2: C0 coverage + loop coverage'
-- text: What is software testing?
+- text: 'Gọi X là dòng đời (thời gian làm việc tốt) của sản phẩm ổ cứng máy tính (tính
+    theo năm). Một ổ cứng loại
+
+    ABC có xác suất làm việc tốt sau 9 năm là 0.1. Giả sử hàm mật độ xác suất của
+    X là f(x) = a
+
+    (x+1)b cho x ≥ 0
+
+    với a > 0 và b > 1. Hãy Tính a, b?'
+- text: Thủ đô của nước Pháp là gì?
+- text: How to prove a problem is NP complete problem
 pipeline_tag: text-classification
 inference: true
 model-index:
-- name: SetFit with sentence-transformers/distiluse-base-multilingual-cased-v2
+- name: SetFit with sentence-transformers/all-MiniLM-L6-v2
   results:
   - task:
       type: text-classification
@@ -52,13 +59,13 @@ model-index:
       split: test
     metrics:
     - type: accuracy
-      value: 0.5
+      value: 0.6666666666666666
       name: Accuracy
 ---
 
-# SetFit with sentence-transformers/distiluse-base-multilingual-cased-v2
+# SetFit with sentence-transformers/all-MiniLM-L6-v2
 
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/distiluse-base-multilingual-cased-v2](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-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/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-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:
 
@@ -69,9 +76,9 @@ The model has been trained using an efficient few-shot learning technique that i
 
 ### Model Description
 - **Model Type:** SetFit
-- **Sentence Transformer body:** [sentence-transformers/distiluse-base-multilingual-cased-v2](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2)
+- **Sentence Transformer body:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)
 - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
-- **Maximum Sequence Length:** 128 tokens
+- **Maximum Sequence Length:** 256 tokens
 - **Number of Classes:** 2 classes
 <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 <!-- - **Language:** Unknown -->
@@ -84,17 +91,17 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
 ### Model Labels
-| Label | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
-|:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| 0     | <ul><li>'What is the capital of France?'</li><li>'Nêu ngắn g���n về quá trình quang hợp.'</li><li>'Briefly describe the concept of photosynthesis.'</li></ul>                                                                                                                                                                                                                                                                                                                                                                                              |
-| 1     | <ul><li>'What is White-box testing?\nCâu hỏi 7Trả lời\n\na.\nAll of the other answers.\n\nb.\nA testing technique in which internal structure, design and coding of software are tested.\n\nc.\nIts foundation is to execute every part of the code at least once.\n\nd.\nIn this technique, code is visible to testers.'</li><li>'For the expression "(a AND (b OR c))", which of the following test-cases is Multiple Condition Coverage (MCC)?'</li><li>'The p success of karger min cut after k steps. Tell me the detail of the equation'</li></ul> |
+| Label | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+|:------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 0     | <ul><li>'what is microservices'</li><li>'What is the capital of France?'</li><li>'Write a Python function that calculates the factorial of a number.'</li></ul>                                                                                                                                                                                                                                                                                                                             |
+| 1     | <ul><li>'Tell me the difference between microservice and service based architecture'</li><li>'What is White-box testing?\nCâu hỏi 7Trả lời\n\na.\nAll of the other answers.\n\nb.\nA testing technique in which internal structure, design and coding of software are tested.\n\nc.\nIts foundation is to execute every part of the code at least once.\n\nd.\nIn this technique, code is visible to testers.'</li><li>'Analyze the time complexity of the merge sort algorithm.'</li></ul> |
 
 ## Evaluation
 
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.5      |
+| **all** | 0.6667   |
 
 ## Uses
 
@@ -114,7 +121,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("chibao24/model_routing_few_shot")
 # Run inference
-preds = model("What is software testing?")
+preds = model("Thủ đô của nước Pháp là gì?")
 ```
 
 <!--
@@ -146,7 +153,7 @@ preds = model("What is software testing?")
 ### Training Set Metrics
 | Training set | Min | Median  | Max |
 |:-------------|:----|:--------|:----|
-| Word count   | 3   | 20.2903 | 115 |
+| Word count   | 3   | 20.1613 | 115 |
 
 | Label | Training Sample Count |
 |:------|:----------------------|
@@ -173,21 +180,21 @@ preds = model("What is software testing?")
 ### Training Results
 | Epoch   | Step    | Training Loss | Validation Loss |
 |:-------:|:-------:|:-------------:|:---------------:|
-| 0.0078  | 1       | 0.4319        | -               |
-| 0.3906  | 50      | 0.1028        | -               |
-| 0.7812  | 100     | 0.0021        | -               |
-| **1.0** | **128** | **-**         | **0.2328**      |
-| 1.1719  | 150     | 0.0002        | -               |
-| 1.5625  | 200     | 0.0           | -               |
-| 1.9531  | 250     | 0.0001        | -               |
-| 2.0     | 256     | -             | 0.3315          |
-| 2.3438  | 300     | 0.0           | -               |
-| 2.7344  | 350     | 0.0002        | -               |
-| 3.0     | 384     | -             | 0.2364          |
-| 3.125   | 400     | 0.0001        | -               |
-| 3.5156  | 450     | 0.0           | -               |
-| 3.9062  | 500     | 0.0001        | -               |
-| 4.0     | 512     | -             | 0.3333          |
+| 0.0078  | 1       | 0.5129        | -               |
+| 0.3906  | 50      | 0.2717        | -               |
+| 0.7812  | 100     | 0.0941        | -               |
+| **1.0** | **128** | **-**         | **0.1068**      |
+| 1.1719  | 150     | 0.0434        | -               |
+| 1.5625  | 200     | 0.0075        | -               |
+| 1.9531  | 250     | 0.005         | -               |
+| 2.0     | 256     | -             | 0.1193          |
+| 2.3438  | 300     | 0.0088        | -               |
+| 2.7344  | 350     | 0.0027        | -               |
+| 3.0     | 384     | -             | 0.1587          |
+| 3.125   | 400     | 0.0023        | -               |
+| 3.5156  | 450     | 0.0013        | -               |
+| 3.9062  | 500     | 0.0011        | -               |
+| 4.0     | 512     | -             | 0.1103          |
 
 * The bold row denotes the saved checkpoint.
 ### Framework Versions

config.json

@@ -1,26 +1,26 @@
 {
   "_name_or_path": "checkpoints/step_128",
-  "activation": "gelu",
   "architectures": [
-    "DistilBertModel"
+    "BertModel"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
   "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_hidden_states": true,
-  "output_past": true,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "vocab_size": 119547
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699c83648fa8570f6733bd6022605955a6fd5cb9f189f6b21d7e076466ea8357
-size 538947416
+oid sha256:c468dfd44193ef693a8d09bce5c59d85fc8a9aa41218a2ec86ab04225765fb05
+size 90864192

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846cbc06ae8101739d4132eefe3efa2ad30a334c426d9ba19156743aefac24c8
-size 4959
+oid sha256:e40b9d894c95698d7361aabf58fa14f74ab3965a57923f78d7294efa2db4e5a4
+size 3935

modules.json

@@ -14,7 +14,7 @@
   {
     "idx": 2,
     "name": "2",
-    "path": "2_Dense",
-    "type": "sentence_transformers.models.Dense"
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
   }
 ]

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 128,
+  "max_seq_length": 256,
   "do_lower_case": false
 }

tokenizer_config.json

@@ -44,12 +44,10 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "full_tokenizer_file": null,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_len": 512,
   "max_length": 128,
-  "model_max_length": 128,
+  "model_max_length": 256,
   "never_split": null,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
@@ -59,7 +57,7 @@
   "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"