tmutton commited on
Commit
0b0bca8
·
verified ·
1 Parent(s): a41f38e

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +42 -0
  2. model.safetensors +3 -0
  3. predict.py +49 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +15 -0
  6. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "1.3.1 Info and Relationships",
15
+ "1": "2.1.1 Keyboard",
16
+ "2": "2.4.3 Focus Order",
17
+ "3": "2.4.7 Focus Visible",
18
+ "4": "4.1.2 Name, Role, Value"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "label2id": {
22
+ "1.3.1 Info and Relationships": 0,
23
+ "2.1.1 Keyboard": 1,
24
+ "2.4.3 Focus Order": 2,
25
+ "2.4.7 Focus Visible": 3,
26
+ "4.1.2 Name, Role, Value": 4
27
+ },
28
+ "max_position_embeddings": 512,
29
+ "model_type": "distilbert",
30
+ "n_heads": 12,
31
+ "n_layers": 6,
32
+ "pad_token_id": 0,
33
+ "problem_type": "single_label_classification",
34
+ "qa_dropout": 0.1,
35
+ "seq_classif_dropout": 0.2,
36
+ "sinusoidal_pos_embds": false,
37
+ "tie_weights_": true,
38
+ "tie_word_embeddings": true,
39
+ "transformers_version": "5.17.0",
40
+ "use_cache": false,
41
+ "vocab_size": 30522
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e339ce027995e2d50ed682adfaaa0aaad8bf4fb626943da9d288effc1d2b4102
3
+ size 267841796
predict.py ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import torch
2
+
3
+ from transformers import (
4
+ AutoModelForSequenceClassification,
5
+ AutoTokenizer,
6
+ )
7
+
8
+ MODEL_PATH = "."
9
+
10
+ tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
11
+
12
+ model = AutoModelForSequenceClassification.from_pretrained(
13
+ MODEL_PATH
14
+ )
15
+
16
+
17
+ def predict(text):
18
+ inputs = tokenizer(
19
+ text,
20
+ return_tensors="pt",
21
+ truncation=True,
22
+ )
23
+
24
+ with torch.no_grad():
25
+ outputs = model(**inputs)
26
+
27
+ probabilities = torch.softmax(
28
+ outputs.logits,
29
+ dim=-1
30
+ )[0]
31
+
32
+ predicted_id = torch.argmax(probabilities).item()
33
+
34
+ predicted_label = model.config.id2label[predicted_id]
35
+ confidence = probabilities[predicted_id].item()
36
+
37
+ return predicted_label, confidence
38
+
39
+
40
+ while True:
41
+ text = input("\nDescribe an accessibility issue (or 'quit'): ")
42
+
43
+ if text.lower() == "quit":
44
+ break
45
+
46
+ label, confidence = predict(text)
47
+
48
+ print(f"\nPrediction: {label}")
49
+ print(f"Confidence: {confidence:.1%}")
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b04d66d7602bacf6fdd33590e9ee07eb0f9a53aa2a53037858a002704e58dd5
3
+ size 5201