GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Mohamedabul
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Mohamedabul
Model Tree
Input Modalities
Output Modalities
Supported Functionality
This LLM acts as an expert cybersecurity analyst and reverse engineer. It is capable of:
To achieve maximum accuracy, the model was fine-tuned on an expansive historical corpus of modern vulnerabilities and exploits, completely uncapped and unfiltered:
The fine-tuned model was evaluated against an unseen hold-out test dataset to mathematically verify its understanding of cybersecurity concepts and generation quality.
| Metric | Score | Interpretation |
|---|---|---|
| Perplexity | 7.61 | Excellent. Reflects high confidence and deep vocabulary retention for security concepts. |
| METEOR | 0.4084 | Very Good. The model captures semantic meaning effectively, correctly utilizing security synonyms. |
| ROUGE-1 | 0.3496 | High structural and unigram overlap with security researcher standards. |
| ROUGE-L | 0.2044 | Consistent sentence-level alignment for technical vulnerability reports. |
To load the model quickly using Unsloth for 2x faster inference:
python
from unsloth import FastLanguageModel # Load the model directly from this Hugging Face repositorymodel, tokenizer = FastLanguageModel.from_pretrained( model_name="Mohamedabul/Qwen2.5-3B-CyberSec-Instruct", # or your exact repo name max_seq_length=1024, dtype=None, load_in_4bit=True,)FastLanguageModel.for_inference(model) # Example Promptinstruction = "Analyze this vulnerability: CVE-2021-44228 (Log4Shell). Provide attack vectors, severity, and mitigation."prompt = tokenizer.apply_chat_template( [{"role": "user", "content": instruction}], tokenize=False, add_generation_prompt=True) inputs = tokenizer([prompt], return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=256, use_cache=True)print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])from unsloth import FastLanguageModel # Load the model directly from this Hugging Face repositorymodel, tokenizer = FastLanguageModel.from_pretrained( model_name="Mohamedabul/Qwen2.5-3B-CyberSec-Instruct", # or your exact repo name max_seq_length=1024, dtype=None, load_in_4bit=True,)FastLanguageModel.for_inference(model) # Example Promptinstruction = "Analyze this vulnerability: CVE-2021-44228 (Log4Shell). Provide attack vectors, severity, and mitigation."prompt = tokenizer.apply_chat_template( [{"role": "user", "content": instruction}], tokenize=False, add_generation_prompt=True) inputs = tokenizer([prompt], return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=256, use_cache=True)print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])