trollek/setfit-gibberish-detector
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: trollek/setfit-gibberish-detector
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-25 19:15:19 +08:00
commit 26cd9dfa31
14 changed files with 61454 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View File

@@ -0,0 +1,34 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

10
1_Pooling/config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"word_embedding_dimension": 384,
"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
}

30
README.md Normal file
View File

@@ -0,0 +1,30 @@
---
pipeline_tag: text-classification
tags:
- sentence-transformers
- transformers
language:
- en
licence:
- apache-2.0
---
# SetFit-caesar-cipher-classifier
Made to detect whether or not text is gibberish for [bruteforcing Caesar ciphers](https://gist.github.com/hosteren/852202caffa5fa88b317689ff6ea5be8). It did not work anymore, and SetFit has been updated since. I used version 1.1.0 to train this classifier on the [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) model.
## Usage (SetFitModel)
```python
from setfit import SetFitModel
sentences = ["This is an example sentence", "Each sentence is tested", "Aopz pz hu lehtwsl zlualujl", "Rnpu fragrapr vf grfgrq"]
model = SetFitModel.from_pretrained("trollek/setfit-gibberish-detector")
for sentence in sentences:
classification = model.predict(sentence)
print(classification)
# clear
# clear
# gibberish
# gibberish
```

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
"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,
"initializer_range": 0.02,
"intermediate_size": 1536,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 6,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.44.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}

10
config_sentence_transformers.json Normal file
View File

@@ -0,0 +1,10 @@
{
"__version__": {
"sentence_transformers": "3.1.1",
"transformers": "4.44.2",
"pytorch": "2.4.1"
},
"prompts": {},
"default_prompt_name": null,
"similarity_fn_name": null
}

7
config_setfit.json Normal file
View File

@@ -0,0 +1,7 @@
{
"labels": [
"gibberish",
"clear"
],
"normalize_embeddings": false
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c79bbb4e9587c8f0ce09e764f5cea19c6f4eb3fbc17dd29a09fa6cfb2df34d00
size 90864192

3
model_head.pkl Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c1e685aa2ec6b1b042e31383a40d3502f460de91b90650c66eb1f51709137d6a
size 3989

20
modules.json Normal file
View File

@@ -0,0 +1,20 @@
[
{
"idx": 0,
"name": "0",
"path": "",
"type": "sentence_transformers.models.Transformer"
},
{
"idx": 1,
"name": "1",
"path": "1_Pooling",
"type": "sentence_transformers.models.Pooling"
},
{
"idx": 2,
"name": "2",
"path": "2_Normalize",
"type": "sentence_transformers.models.Normalize"
}
]

4
sentence_bert_config.json Normal file
View File

@@ -0,0 +1,4 @@
{
"max_seq_length": 256,
"do_lower_case": false
}

37
special_tokens_map.json Normal file
View File

@@ -0,0 +1,37 @@
{
"cls_token": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

30684
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

64
tokenizer_config.json Normal file
View File

@@ -0,0 +1,64 @@
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"max_length": 128,
"model_max_length": 256,
"never_split": null,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "[SEP]",
"stride": 0,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}

30522
vocab.txt Normal file
View File

File diff suppressed because it is too large Load Diff