Downloads · 30 days
11
11% of all-time downloads
lotl-deepseek-14b
art0xx/lotl-deepseek-14b
lotl-deepseek-14b is a text generation model from art0xx. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
LoRA adapter fine-tuned for Living Off the Land (LOTL) cybersecurity.
All-time downloads
99
Public
Repo size
14.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors275 MB · 96%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- fc1a7ee8
Try a prompt
Base models
Model card
From the Hugging Face model README
lotl-deepseek-14b (LoRA Adapter)
LoRA adapter fine-tuned for Living Off the Land (LOTL) cybersecurity.
Model Details
| Attribute | Value |
|---|---|
| Base Model | unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit |
| Method | QLoRA (4-bit) |
| Size | 275 MB |
| Training | 1.9 hours on RTX 5090 |
| Loss | 0.78 |
| Dataset | 4,086 LOTL Q&A examples |
Quick Start
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
BASE = "unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit"
ADAPTER = "art0xx/lotl-deepseek-14b"
model = AutoModelForCausalLM.from_pretrained(BASE, load_in_4bit=True)
model = PeftModel.from_pretrained(model, ADAPTER)
tokenizer = AutoTokenizer.from_pretrained(BASE)
messages = [
{"role": "system", "content": "You are a LOTL cybersecurity assistant."},
{"role": "user", "content": "How do attackers use certutil?"},
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026