Instructions to use xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2 with Transformers:

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

pipe = pipeline("text-generation", model="xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2")
model = AutoModelForCausalLM.from_pretrained("xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2

SGLang

How to use xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2 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 "xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2" \
    --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": "xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2",
		"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 "xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2" \
        --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": "xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2 with Docker Model Runner:
```
docker model run hf.co/xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2
```

seccodeplt-qwen2.5-coder-3b-diff-sft-v2

Token-diff supervised fine-tuning for the SecCodePLT+ compliance experiment using Qwen/Qwen2.5-Coder-3B-Instruct. This v2 run corrects causal-label alignment and uses the official ReaL safety-unit-test reward with DAPO-style token loss and dynamic sampling. Training used seed 42 and the official 655-example training split. Evaluation used greedy decoding on all 164 official test examples.

Evaluation

Metric	Value
Mean reward	0.369882
Output format pass	95.73%
Syntax pass	95.73%
Capability pass	24.39%
Safety pass	55.49%
Joint pass	18.90%

Limitations

This is a single-seed research checkpoint evaluated with the benchmark's resource-bounded Python verifier. It is not a general guarantee of secure code.

Downloads last month: 144

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

Qwen/Qwen2.5-Coder-3B-Instruct

Finetuned

(137)

this model

xw1234gan
/

seccodeplt-qwen2.5-coder-3b-diff-sft-v2

seccodeplt-qwen2.5-coder-3b-diff-sft-v2

Evaluation

Limitations

Model tree for xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2

Dataset used to train xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2