Instructions to use xtools-at/SmolPhish3-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xtools-at/SmolPhish3-3B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="xtools-at/SmolPhish3-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("xtools-at/SmolPhish3-3B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xtools-at/SmolPhish3-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xtools-at/SmolPhish3-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xtools-at/SmolPhish3-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xtools-at/SmolPhish3-3B

SGLang

How to use xtools-at/SmolPhish3-3B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "xtools-at/SmolPhish3-3B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xtools-at/SmolPhish3-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "xtools-at/SmolPhish3-3B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xtools-at/SmolPhish3-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xtools-at/SmolPhish3-3B with Docker Model Runner:
```
docker model run hf.co/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.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for xtools-at/SmolPhish3-3B

Base model

HuggingFaceTB/SmolLM3-3B-Base

Finetuned

HuggingFaceTB/SmolLM3-3B

Finetuned

K0D3IN/SmolLM3-3B-Instruct-heretic

Finetuned

(2)

this model

xtools-at
/

SmolPhish3-3B

SmolPhish3

Example use

System prompt

Example user prompt

Model tree for xtools-at/SmolPhish3-3B

Dataset used to train xtools-at/SmolPhish3-3B