lablab-ai-amd-developer-hackathon/Qwen-security-builder-14b

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "lablab-ai-amd-developer-hackathon/security-builder-14b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

###  💬 Example Usage (JSON Mode)
messages = [
    {"role": "user", "content": "Fix the buffer overflow and return JSON with keys: fixed_code, explanation, cwe_mitigated."}
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    output = model.generate(**inputs, max_new_tokens=512, temperature=0.1)

import json
print(json.loads(tokenizer.decode(output[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)))