PEFT
Safetensors
dafny
formal-verification
loop-invariants
lora

You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Qwen2.5-Coder-0.5B-Instruct_reform-dafny-loop-inv-gen_SFT

Qwen/Qwen2.5-Coder-0.5B-Instruct fine-tuned to add loop invariants to Dafny programs so that they verify, on ThuraAung1601/reform-dafny-loop-inv-gen: LoRA SFT. Trained without natural-language chain of thought: the output is the complete program.

DafnyBench-cleaned (pass@1, 733 tasks): 47.89% solved (base model: 23.33%).

from peft import AutoPeftModelForCausalLM
model = AutoPeftModelForCausalLM.from_pretrained("ThuraAung1601/Qwen2.5-Coder-0.5B-Instruct_reform-dafny-loop-inv-gen_SFT")

Prompt -- system message:

You are an expert in Dafny formal verification. You are given a Dafny program whose loops are missing their loop invariants. Output the complete program with loop invariants added so that it verifies with `dafny verify`. Do not change anything else in the program. Output only the program in a ```dafny code block.

user message: the program inside a ```dafny code block.

Downloads last month
15
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ThuraAung1601/Qwen2.5-Coder-0.5B-Instruct_reform-dafny-loop-inv-gen_SFT

Adapter
(86)
this model

Dataset used to train ThuraAung1601/Qwen2.5-Coder-0.5B-Instruct_reform-dafny-loop-inv-gen_SFT