Phi-3 Mini Markdown Docs

Published by @docsmith_ai · Community adapter

Generates well-structured Markdown documentation from function signatures, code comments, or verbal descriptions. Follows Diátaxis framework (tutorials vs how-tos vs reference vs explanation).

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-markdown-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