Instructions to use rudycaz/qwen35-27b-phish-finetuned-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rudycaz/qwen35-27b-phish-finetuned-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rudycaz/qwen35-27b-phish-finetuned-gguf",
	filename="qwen35-27b-phish-finetuned-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use rudycaz/qwen35-27b-phish-finetuned-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M

Use Docker

docker model run hf.co/rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use rudycaz/qwen35-27b-phish-finetuned-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rudycaz/qwen35-27b-phish-finetuned-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rudycaz/qwen35-27b-phish-finetuned-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M

Ollama
How to use rudycaz/qwen35-27b-phish-finetuned-gguf with Ollama:
```
ollama run hf.co/rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M
```

Unsloth Studio

How to use rudycaz/qwen35-27b-phish-finetuned-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for rudycaz/qwen35-27b-phish-finetuned-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for rudycaz/qwen35-27b-phish-finetuned-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rudycaz/qwen35-27b-phish-finetuned-gguf to start chatting

How to use rudycaz/qwen35-27b-phish-finetuned-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use rudycaz/qwen35-27b-phish-finetuned-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use rudycaz/qwen35-27b-phish-finetuned-gguf with Docker Model Runner:
```
docker model run hf.co/rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M
```

Lemonade

How to use rudycaz/qwen35-27b-phish-finetuned-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rudycaz/qwen35-27b-phish-finetuned-gguf:Q4_K_M

Run and chat with the model

lemonade run user.qwen35-27b-phish-finetuned-gguf-Q4_K_M

List all available models

lemonade list

rudycaz commited on Mar 4

Commit

43b3683

verified ·

1 Parent(s): 249aba6

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -25

README.md CHANGED Viewed

@@ -1,5 +1,3 @@
-```markdown
 ---
 license: apache-2.0
 base_model: Qwen/Qwen3.5-27B
@@ -9,39 +7,24 @@ tags:
   - llama.cpp
   - lm-studio
   - qwen
-  - phishing
-  - email-security
 language:
   - en
 ---
-# qwen35-27b-phish-finetuned-gguf (LM Studio / llama.cpp)
-This repository provides **GGUF** files for a phishing-focused fine-tuned model derived from:
-- Base model: `Qwen/Qwen3.5-27B`
-- Fine-tuning: QLoRA adapter trained for **PHISHING vs LEGIT** classification
-- Export: adapter merged into base → converted to GGUF → (optionally) quantized
-## Recommended file
-- `qwen35-27b-phish-finetuned-q4_k_m.gguf` (recommended default for most local setups)
-(If you uploaded multiple quantizations, list them all under “Files”.)
-## Use in LM Studio
-### Option A: Download from Hugging Face in LM Studio
-1. Open LM Studio
-2. Search for this repo/model and download the `.gguf`
-3. Load it in the chat UI
-### Option B: Import a GGUF you downloaded manually
-```bash
-lms import /path/to/qwen35-27b-phish-finetuned-q4_k_m.gguf
 You are a security assistant. Classify the following email as PHISHING or LEGIT.
 EMAIL:
 <paste email here>
-Answer with exactly one word: PHISHING or LEGIT.

 ---
 license: apache-2.0
 base_model: Qwen/Qwen3.5-27B
   - llama.cpp
   - lm-studio
   - qwen
 language:
   - en
 ---
+# qwen35-27b-phish-finetuned-gguf
+GGUF export of a phishing-focused fine-tune derived from **Qwen/Qwen3.5-27B** for use in **LM Studio** / **llama.cpp**.
+## Files
+- `qwen35-27b-phish-finetuned-q4_k_m.gguf` — recommended
+## Prompt format
+This model is intended to output one word: `PHISHING` or `LEGIT`.
+```text
 You are a security assistant. Classify the following email as PHISHING or LEGIT.
 EMAIL:
 <paste email here>
+Answer with exactly one word: PHISHING or LEGIT.