Spaces:
Sleeping
Sleeping
Commit Β·
76955f7
1
Parent(s): 03a98ed
aggiunto recupero modello bert da HF hub
Browse files- .gitignore +1 -1
- README.md +0 -2
- data/model/bpo_bert_model/config.json +0 -39
- data/model/bpo_bert_model/tokenizer.json +0 -0
- data/model/bpo_bert_model/tokenizer_config.json +0 -14
- modules/bpo_dispatcher.py +18 -12
.gitignore
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
__pycache__/
|
|
|
|
| 1 |
+
__pycache__/
|
README.md
CHANGED
|
@@ -77,8 +77,6 @@ ngt-ai-platform/
|
|
| 77 |
βββ modules/ # Logica di business
|
| 78 |
βββ data/
|
| 79 |
βββ model/ # CARTELLA MODELLI (Non versionata)
|
| 80 |
-
β βββ bpo_bert_model/ # Cartella del modello BERT addestrato
|
| 81 |
-
β βββ ... # modelli addestrati da noi
|
| 82 |
βββ gallery/ # Immagini di esempio per la Demo
|
| 83 |
βββ tokenizer/ # tokenizer per la BinaryClassification e MultiClassification
|
| 84 |
|
|
|
|
| 77 |
βββ modules/ # Logica di business
|
| 78 |
βββ data/
|
| 79 |
βββ model/ # CARTELLA MODELLI (Non versionata)
|
|
|
|
|
|
|
| 80 |
βββ gallery/ # Immagini di esempio per la Demo
|
| 81 |
βββ tokenizer/ # tokenizer per la BinaryClassification e MultiClassification
|
| 82 |
|
data/model/bpo_bert_model/config.json
DELETED
|
@@ -1,39 +0,0 @@
|
|
| 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": "LABEL_0",
|
| 15 |
-
"1": "LABEL_1",
|
| 16 |
-
"2": "LABEL_2"
|
| 17 |
-
},
|
| 18 |
-
"initializer_range": 0.02,
|
| 19 |
-
"label2id": {
|
| 20 |
-
"LABEL_0": 0,
|
| 21 |
-
"LABEL_1": 1,
|
| 22 |
-
"LABEL_2": 2
|
| 23 |
-
},
|
| 24 |
-
"max_position_embeddings": 512,
|
| 25 |
-
"model_type": "distilbert",
|
| 26 |
-
"n_heads": 12,
|
| 27 |
-
"n_layers": 6,
|
| 28 |
-
"output_past": true,
|
| 29 |
-
"pad_token_id": 0,
|
| 30 |
-
"problem_type": "single_label_classification",
|
| 31 |
-
"qa_dropout": 0.1,
|
| 32 |
-
"seq_classif_dropout": 0.2,
|
| 33 |
-
"sinusoidal_pos_embds": false,
|
| 34 |
-
"tie_weights_": true,
|
| 35 |
-
"tie_word_embeddings": true,
|
| 36 |
-
"transformers_version": "5.0.0",
|
| 37 |
-
"use_cache": false,
|
| 38 |
-
"vocab_size": 119547
|
| 39 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
data/model/bpo_bert_model/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
data/model/bpo_bert_model/tokenizer_config.json
DELETED
|
@@ -1,14 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"backend": "tokenizers",
|
| 3 |
-
"cls_token": "[CLS]",
|
| 4 |
-
"do_lower_case": false,
|
| 5 |
-
"is_local": false,
|
| 6 |
-
"mask_token": "[MASK]",
|
| 7 |
-
"model_max_length": 512,
|
| 8 |
-
"pad_token": "[PAD]",
|
| 9 |
-
"sep_token": "[SEP]",
|
| 10 |
-
"strip_accents": null,
|
| 11 |
-
"tokenize_chinese_chars": true,
|
| 12 |
-
"tokenizer_class": "DistilBertTokenizer",
|
| 13 |
-
"unk_token": "[UNK]"
|
| 14 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
modules/bpo_dispatcher.py
CHANGED
|
@@ -17,23 +17,29 @@ LABELS_MAP = {
|
|
| 17 |
2: "Retention / Churn Risk"
|
| 18 |
}
|
| 19 |
|
|
|
|
|
|
|
| 20 |
class BPODispatcher:
|
| 21 |
-
def __init__(self,
|
| 22 |
self.model = None
|
| 23 |
self.tokenizer = None
|
| 24 |
self.nlp = None
|
| 25 |
-
self.device = "cpu"
|
| 26 |
|
| 27 |
-
# 1. BERT
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
# 2. spaCy
|
| 39 |
try:
|
|
|
|
| 17 |
2: "Retention / Churn Risk"
|
| 18 |
}
|
| 19 |
|
| 20 |
+
MODEL_REPO_ID = "NextGenTech/bpo-bert-model"
|
| 21 |
+
|
| 22 |
class BPODispatcher:
|
| 23 |
+
def __init__(self, model_id=MODEL_REPO_ID):
|
| 24 |
self.model = None
|
| 25 |
self.tokenizer = None
|
| 26 |
self.nlp = None
|
| 27 |
+
self.device = "cpu" # In uno Space CPU basic, usa "cuda" solo se hai GPU
|
| 28 |
|
| 29 |
+
# 1. BERT (Caricamento da Hugging Face Hub)
|
| 30 |
+
print(f"π Tentativo di caricamento modello da: {model_id}...")
|
| 31 |
+
try:
|
| 32 |
+
# token=True usa automaticamente il Secret 'HF_TOKEN' dello Space
|
| 33 |
+
self.tokenizer = DistilBertTokenizerFast.from_pretrained(model_id, token=True)
|
| 34 |
+
self.model = DistilBertForSequenceClassification.from_pretrained(model_id, token=True)
|
| 35 |
+
self.model.to(self.device)
|
| 36 |
+
self.model.eval()
|
| 37 |
+
print("β
Modello BERT scaricato e caricato con successo.")
|
| 38 |
+
except OSError as e:
|
| 39 |
+
print(f"β Errore: Impossibile scaricare il modello. Verifica il Token e il Repo ID.")
|
| 40 |
+
print(f"Dettagli: {e}")
|
| 41 |
+
except Exception as e:
|
| 42 |
+
print(f"β Errore generico BERT: {e}")
|
| 43 |
|
| 44 |
# 2. spaCy
|
| 45 |
try:
|