Instructions to use Veri-Code/ReForm-SFT-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Veri-Code/ReForm-SFT-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="Veri-Code/ReForm-SFT-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Veri-Code/ReForm-SFT-1.5B")
model = AutoModelForCausalLM.from_pretrained("Veri-Code/ReForm-SFT-1.5B")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Veri-Code/ReForm-SFT-1.5B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Veri-Code/ReForm-SFT-1.5B

SGLang

How to use Veri-Code/ReForm-SFT-1.5B 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 "Veri-Code/ReForm-SFT-1.5B" \
    --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": "Veri-Code/ReForm-SFT-1.5B",
		"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 "Veri-Code/ReForm-SFT-1.5B" \
        --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": "Veri-Code/ReForm-SFT-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Veri-Code/ReForm-SFT-1.5B with Docker Model Runner:
```
docker model run hf.co/Veri-Code/ReForm-SFT-1.5B
```

Add comprehensive model card including paper, code, and usage with relevant tags

by nielsr HF Staff - opened Jul 25, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+94

-3

nielsr

Jul 25, 2025

This PR significantly enhances the model card for Qwen2.5-Coder-1.5B by adding:

Detailed information about the paper Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny.
Links to the official project page and GitHub repository.
The library_name: transformers and pipeline_tag: text-generation metadata tags, enabling better discoverability and user experience (e.g., "Use in Transformers" button).
Additional descriptive tags: code-generation, reinforcement-learning, formal-verification, and qwen2 for improved searchability.
A Python code snippet for quick inference, demonstrating how to use the model with the transformers library.
The official BibTeX citation.

This enhancement will greatly benefit users looking to understand and utilize the model.

Add comprehensive model card including paper, code, and usage with relevant tags4919976e

SiniShell1 changed pull request status to merged Jul 25, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment