Instructions to use ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO")
model = AutoModelForCausalLM.from_pretrained("ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO

SGLang

How to use ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO with Docker Model Runner:
```
docker model run hf.co/ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO
```

Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO

Qwen/Qwen2.5-Coder-1.5B-Instruct fine-tuned to add loop invariants to Dafny programs so that they verify, on ThuraAung1601/reform-dafny-loop-inv-gen: LoRA SFT followed by LoRA GRPO whose reward comes only from the Dafny verifier (Re:Form-style: syntax 0.2 / verified 1.0, with a faithfulness gate against editing the program or its spec). Trained without natural-language chain of thought: the output is the complete program.

DafnyBench-cleaned (pass@1, 733 tasks): 51.16% solved (base model: 11.19%).

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO")      # base + SFT + GRPO, merged
tokenizer = AutoTokenizer.from_pretrained("ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO")

The GRPO LoRA adapter alone is in lora/; it applies on top of the merged SFT model.

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: 306

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B-Instruct

Adapter

(187)

this model

ThuraAung1601
/

Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO

Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO

Model tree for ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO

Dataset used to train ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO