Model Intelligence Sheet
xtools-at/SmolPhish3-3B-GGUF overview
SmolMed3 3B : GGUF Static quants in GGUF format of xtools at/SmolPhish3 3B https://huggingface.co/xtools at/SmolPhish3 3B SmolPhish3 LoRA fine tune of SmolLM3 …
Runs locally from ~1.78 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | xtools-at/SmolPhish3-3B-GGUF |
|---|---|
| Author | xtools-at |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | K0D3IN/SmolLM3-3B-Instruct-heretic |
| Last modified | 2026-09-19T22:06:36.000Z |
Model README
---
base_model: K0D3IN/SmolLM3-3B-Instruct-heretic
tags:
- gguf
- llama.cpp
- llama-cpp
- smollm3
- heretic
license: apache-2.0
language:
- en
datasets:
- kxm1k4m1/generate_phishing_email_final
pipeline_tag: text-generation
---
SmolMed3-3B : GGUF
Static quants in GGUF format of xtools-at/SmolPhish3-3B
---
SmolPhish3
LoRA fine-tune of SmolLM3 for generating (relatively obvious) phishing mails, for research use only.
- Finetuned from model: K0D3IN/SmolLM3-3B-Instruct-heretic
- Dataset used: kxm1k4m1/generate_phishing_email_final
Example use
Following the schema laid out in the training dataset:
System prompt
Generate a convincing phishing email based on the given personal context.
Example user prompt
Using the following personal details, craft a convincing phishing email that leverages the person's job position and recent activities. The email should create urgency and prompt the user to click a link or perform a similar malicious action.
Name: John Doe Johnson
Email: jd@company.com
Job Position: Recruiter
Recent Activities (use these to make the email highly relevant):
- Implementing a new empower interactive e-services system
Generate ONLY the text of the phishing email, starting with the 'Subject:' line. Ensure it is well-formatted and appears like a real email.Run xtools-at/SmolPhish3-3B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models