Add SetFit model

1_Pooling/config.json

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

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: cross-encoder/ms-marco-MiniLM-L-6-v2
+base_model: basel/ATTACK-BERT
 library_name: setfit
 metrics:
 - accuracy
@@ -10,21 +10,24 @@ tags:
 - text-classification
 - generated_from_setfit_trainer
 widget:
-- text: The internal DRBG state value of the RNG is stored in NVRAM for persistent
-    use.
-- text: X9.31 PRNG seed keys Triple-DES (112 bit) Generated by gathering entropy.
-- text: A hardware noise source is used as a non-Approved RNG to generate seed material
-    (consisting of random sequences of ones and zeroes) for the FIPS-approved RNG.
-- text: ANSI X9.31 RNG Seed Key 168-bit TDES keys/ 256-bit AES key Generated by the
-    TRNG.
-- text: X9.31 PRNG seed keys Triple-DES (112 bit) Generated by gathering entropy RAM
-    only
+- text: With the exception of the DHSK and the RNG seed, all critical security parameters
+    are loaded during manufacturing.
+- text: The private key component of an ANSI X9.31-compliant PRNG is stored securely
+    in NVRAM.
+- text: This DRNG uses an 8-byte Seed and an 16-byte Seed Key as inputs to the DRNG.
+    The seed & seed-key values are generated by the hardware RNG and stored only in
+    RAM. These values are zeroized when the module is reset in contact mode or when
+    the module is deselected in contactless mode.
+- text: The seed key is used as an input to the X9.31 RNG, a deterministic random
+    number generator, and is generally not stored long term.
+- text: PRNG seed key X9.31 SDRAM This is the seed key for the PRNG. It is statically
+    stored in the code.
 inference: true
 ---
 
-# SetFit with cross-encoder/ms-marco-MiniLM-L-6-v2
+# SetFit with basel/ATTACK-BERT
 
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [cross-encoder/ms-marco-MiniLM-L-6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-6-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 [basel/ATTACK-BERT](https://huggingface.co/basel/ATTACK-BERT) 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:
 
@@ -35,9 +38,9 @@ The model has been trained using an efficient few-shot learning technique that i
 
 ### Model Description
 - **Model Type:** SetFit
-- **Sentence Transformer body:** [cross-encoder/ms-marco-MiniLM-L-6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-6-v2)
+- **Sentence Transformer body:** [basel/ATTACK-BERT](https://huggingface.co/basel/ATTACK-BERT)
 - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
-- **Maximum Sequence Length:** 512 tokens
+- **Maximum Sequence Length:** 384 tokens
 - **Number of Classes:** 2 classes
 <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 <!-- - **Language:** Unknown -->
@@ -50,10 +53,10 @@ 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                                                                                                                                                                                                                                                                                                                                                                                 |
-|:---------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| positive | <ul><li>'PRNG seed key Pre-loaded during the manufacturing process, compiled in the binary.'</li><li>'RNG Key ANSI X9.31 AES 128 bits Key used by the Approved RNG underlying encryption algorithm N/A In plaintext in tamper protected memory entered in factory.'</li><li>'The PRNG seed key is pre-loaded during manufacturing and compiled directly into the binary code.'</li></ul> |
-| negative | <ul><li>'The seed key is used as an input to the X9.31 RNG, a deterministic random number generator, and is generally not stored long term.'</li><li>'module stores RNG and DRBG state values only in RAM.'</li><li>'128 bits Random Number Key Key value is used by the random number generator. RTC-RAM Zeroize CSPs service.'</li></ul>                                               |
+| Label    | Examples                                                                                                                                                                                                                                                                                                                                                                                                                                |
+|:---------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| negative | <ul><li>'ANSI X9.31 Appendix A.2.4 PRNG key AES 128-bit key Internally generated Never exits the module Plaintext in volatile memory Rebooting the modules Seeding the FIPS-Approved ANSI X9.31 PRNG'</li><li>'PRNG seed key Continually polled from various system resources to accrue entropy.'</li><li>'module stores RNG and DRBG state values only in RAM.'</li></ul>                                                              |
+| positive | <ul><li>"The PRNG's seed key is encrypted with a device-specific key and securely stored in non-volatile memory."</li><li>'An RNG key compliant with ANSI X9.31 AES 128-bit standards is used by the underlying encryption algorithm and stored in plaintext within tamper-protected memory during factory setup.'</li><li>'The PRNG seed key is pre-loaded during manufacturing and compiled directly into the binary code.'</li></ul> |
 
 ## Uses
 
@@ -73,7 +76,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("yasirdemircan/setfit_rng_v3")
 # Run inference
-preds = model("X9.31 PRNG seed keys Triple-DES (112 bit) Generated by gathering entropy.")
+preds = model("The private key component of an ANSI X9.31-compliant PRNG is stored securely in NVRAM.")
 ```
 
 <!--
@@ -103,14 +106,14 @@ preds = model("X9.31 PRNG seed keys Triple-DES (112 bit) Generated by gathering
 ## Training Details
 
 ### Training Set Metrics
-| Training set | Min | Median | Max |
-|:-------------|:----|:-------|:----|
-| Word count   | 6   | 19.2   | 53  |
+| Training set | Min | Median  | Max |
+|:-------------|:----|:--------|:----|
+| Word count   | 6   | 18.8444 | 59  |
 
 | Label    | Training Sample Count |
 |:---------|:----------------------|
-| negative | 22                    |
-| positive | 23                    |
+| negative | 21                    |
+| positive | 24                    |
 
 ### Training Hyperparameters
 - batch_size: (16, 16)
@@ -133,16 +136,16 @@ preds = model("X9.31 PRNG seed keys Triple-DES (112 bit) Generated by gathering
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.0149 | 1    | 0.1738        | -               |
-| 0.7463 | 50   | 0.3142        | -               |
-| 1.0    | 67   | -             | 0.3065          |
-| 1.4925 | 100  | 0.045         | -               |
-| 2.0    | 134  | -             | 0.2712          |
-| 2.2388 | 150  | 0.0053        | -               |
-| 2.9851 | 200  | 0.0023        | -               |
-| 3.0    | 201  | -             | 0.2794          |
-| 3.7313 | 250  | 0.0018        | -               |
-| 4.0    | 268  | -             | 0.2812          |
+| 0.0149 | 1    | 0.2442        | -               |
+| 0.7463 | 50   | 0.1714        | -               |
+| 1.0    | 67   | -             | 0.1785          |
+| 1.4925 | 100  | 0.0029        | -               |
+| 2.0    | 134  | -             | 0.1880          |
+| 2.2388 | 150  | 0.0004        | -               |
+| 2.9851 | 200  | 0.0003        | -               |
+| 3.0    | 201  | -             | 0.1818          |
+| 3.7313 | 250  | 0.0003        | -               |
+| 4.0    | 268  | -             | 0.1837          |
 
 ### Framework Versions
 - Python: 3.10.15

config.json

@@ -1,33 +1,24 @@
 {
-  "_name_or_path": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+  "_name_or_path": "basel/ATTACK-BERT",
   "architectures": [
-    "BertModel"
+    "MPNetModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "label2id": {
-    "LABEL_0": 0
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
   "transformers_version": "4.45.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30527
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1029baca611f2a3e126c834a86c701b72b455e5f39d50add39f1079b55cf5c8e
-size 90864192
+oid sha256:b25cc944d4dc118c5ae874af016d2f93be1cdc8eaea62e7e5a03e21efc9755d1
+size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf08e868ca18751478ca82efbe18b004171f3fbbb844d906a0b32c27a97c63fc
-size 3983
+oid sha256:8deee61a156ac484a68ce871d613d34b8c40e12e855e641de092d0f0b87423f4
+size 7055

modules.json

@@ -10,5 +10,11 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
   }
 ]

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 512,
+  "max_seq_length": 384,
   "do_lower_case": false
 }

special_tokens_map.json

@@ -1,7 +1,51 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,57 +1,72 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "104": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
   "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 384,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

vocab.txt

@@ -1,3 +1,7 @@
+<s>
+<pad>
+</s>
+<unk>
 [PAD]
 [unused0]
 [unused1]
@@ -30520,3 +30524,4 @@ necessitated
 ##：
 ##？
 ##～
+<mask>