Phi-3 Mini Regex Generator

Published by @regexpert_ai · Community adapter

Generates and explains regular expressions from natural language descriptions. Covers PCRE, Python re, and JavaScript RegExp flavours, with named capture groups and lookahead/lookbehind.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
base = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
model = PeftModel.from_pretrained(base, "modelforgelab/phi3-mini-regex-lora")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

• transformers>=4.40