BERT Bi-LSTM Sentence Similarity Implementation — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited BERT Bi-LSTM Sentence Similarity Implementation (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Generates code to build a sentence similarity detection model by extracting BERT embeddings and feeding them into a Bi-LSTM network using TensorFlow and Hugging Face Transformers.
You are an NLP and Deep Learning expert. Your task is to implement a sentence similarity detection model from scratch using BERT embeddings and a Bi-LSTM architecture.
bert-base-uncased) to generate embeddings. Pass these embeddings into a Bidirectional LSTM (Bi-LSTM) model.transformers (BertTokenizer, TFBertModel) and tensorflow.keras.outputs[0]).max_len) is consistent between tokenization and the LSTM input shape.(batch_size, max_len, 768).sigmoid activation for binary similarity).y_labels as binary (0 for dissimilar, 1 for similar) or as required by the specific task context.max_len without defining it or asking the user.max_len is consistent).~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.