GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Willie999
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Willie999
Model Tree
google/gemma-4-E4B-it
Input Modalities
Output Modalities
Supported Functionality
The model is intended for defensive application security engineering. Direct use-cases include:
trapSTAR can be integrated downstream as a specialized backend engine for:
This model is built strictly under dual-use protection and defensive safety policies. Out-of-scope and prohibited activities include:
Users must execute all suggested patches inside sandboxed staging environments. Security teams should treat the model's output as an assistive recommendation rather than an absolute source of truth.
You do not need to manually format or inject raw ChatML tokens into your input strings. The Hugging Face pipeline architecture parses the structural text array dynamically. Use the code snippet below to run inference:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "Willie999/trapstar" print("Loading tokenizer...")tokenizer = AutoTokenizer.from_pretrained(model_id) print("Loading model directly to CUDA memory map...")model = AutoModelForCausalLM.from_pretrained( model_id, device_map="cuda:0", torch_dtype=torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16,) model.eval() messages = [ { "role": "system", "content": "You are TrapStar, an autonomous defensive security auditing agent. Analyze the provided code snippet, identify the vulnerability type, and write out structural recommendations." }, { "role": "user", "content": """Review this function block for potential vulnerabilities: ```cppvoid process_str(char *str) { char buffer[16]; strcpy(buffer, str);}```""" }] print("\nProcessing chat template serialization...")prompt_text = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)input_ids = tokenizer(prompt_text, return_tensors="pt").input_ids.to("cuda:0") print("Executing direct tensor generation with expanded token limits...")with torch.no_grad(): generated_ids = model.generate( input_ids, max_new_tokens=1536, min_new_tokens=64, temperature=0.2, do_sample=True, pad_token_id=tokenizer.eos_token_id ) response_tokens = generated_ids[0][input_ids.shape[-1]:]response_text = tokenizer.decode(response_tokens, skip_special_tokens=True) print("\n=== Trap Star Defense Output ===")print(response_text)import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "Willie999/trapstar" print("Loading tokenizer...")tokenizer = AutoTokenizer.from_pretrained(model_id) print("Loading model directly to CUDA memory map...")model = AutoModelForCausalLM.from_pretrained( model_id, device_map="cuda:0", torch_dtype=torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16,) model.eval() messages = [ { "role": "system", "content": "You are TrapStar, an autonomous defensive security auditing agent. Analyze the provided code snippet, identify the vulnerability type, and write out structural recommendations." }, { "role": "user", "content": """Review this function block for potential vulnerabilities: ```cppvoid process_str(char *str) { char buffer[16]; strcpy(buffer, str);}```""" }] print("\nProcessing chat template serialization...")prompt_text = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)input_ids = tokenizer(prompt_text, return_tensors="pt").input_ids.to("cuda:0") print("Executing direct tensor generation with expanded token limits...")with torch.no_grad(): generated_ids = model.generate( input_ids, max_new_tokens=1536, min_new_tokens=64, temperature=0.2, do_sample=True, pad_token_id=tokenizer.eos_token_id ) response_tokens = generated_ids[0][input_ids.shape[-1]:]response_text = tokenizer.decode(response_tokens, skip_special_tokens=True) print("\n=== Trap Star Defense Output ===")print(response_text)