# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("dev-analyzer/file_path_model")
model = AutoModelForSequenceClassification.from_pretrained("dev-analyzer/file_path_model")Quick Links
Model for classifying file paths of changed files in git commits for Java projects. This model is based on
bert-base-uncased and fine-tuned.
Categorizes into the following categories:
- Source Code - Core application code typically involving back-end (server-side logic, APIs, database interactions) and front-end (user interface, client-side logic).
- Tests - Code files in a test directory or containing "test".
- Resources - Assets and other resources (images, stylesheets).
- Configuration - Configuration files and scripts (build scripts, manifests, shell scripts).
- Documentation - Software documentation (README files, package-info, license, notice files).
- Downloads last month
- 11
Model tree for dev-analyzer/file_path_model
Base model
google-bert/bert-base-uncased
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="dev-analyzer/file_path_model")