Update README.md

README.md

@@ -1,45 +1,78 @@
 ---
+base_model: mlx-community/Phi-3.5-mini-instruct-4bit
+tags:
+  - mlx
+  - mlx-lm
+  - phi-3.5
+  - peft
+  - lora
+  - phishing
+  - cybersecurity
 language:
-- multilingual
-library_name: mlx
-license: mit
-license_link: https://huggingface.co/microsoft/Phi-3.5-mini-instruct/resolve/main/LICENSE
+  - en
 pipeline_tag: text-generation
-tags:
-- nlp
-- code
-- mlx
-widget:
-- messages:
-  - role: user
-    content: Can you provide ways to eat combinations of bananas and dragonfruits?
-base_model: mlx-community/Phi-3.5-mini-instruct-4bit
 ---
 
-# rudycaz/phi35-phish-mlx
+# phi35-phish-mlx
+
+This repository contains an **Apple MLX**-format phishing-focused model derived from **Phi-3.5 Mini Instruct (4-bit)**. It is intended to help classify suspicious emails and support security review workflows.
+
+## What’s in this repo
+
+This repo is meant to be used in one of these ways:
+
+- **Fused model** (base + adapter merged into a single MLX model directory), OR
+- **Adapter-only** (LoRA adapter weights) to be applied on top of the base model locally
+
+If you are unsure which you uploaded, check the repo file list:
+- Fused model typically includes MLX weights + tokenizer/config files for direct inference.
+- Adapter-only typically includes adapter weight files/config and requires the base model separately.
+
+## Base model
+
+- `mlx-community/Phi-3.5-mini-instruct-4bit`
 
-This model [rudycaz/phi35-phish-mlx](https://huggingface.co/rudycaz/phi35-phish-mlx) was
-converted to MLX format from [mlx-community/Phi-3.5-mini-instruct-4bit](https://huggingface.co/mlx-community/Phi-3.5-mini-instruct-4bit)
-using mlx-lm version **0.30.7**.
+## Dataset
 
-## Use with mlx
+This model was fine-tuned for phishing detection using a Kaggle phishing email dataset:
 
-```bash
-pip install mlx-lm
-```
+- Kaggle dataset: **“phishing-email-dataset”** (naserabdullahalam)  
+  https://www.kaggle.com/datasets/naserabdullahalam/phishing-email-dataset
+
+> If you trained Phi-3.5 on a different Kaggle dataset, replace the link above with the exact dataset URL you used so the citation is accurate.
+
+## Intended behavior
+
+Given an email, the intended output is a single label:
+- `PHISHING`
+- `LEGIT`
+
+Example prompt format:
+```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.
+
+
+pip install -U mlx-lm huggingface_hub
 
-```python
 from mlx_lm import load, generate
 
-model, tokenizer = load("rudycaz/phi35-phish-mlx")
+# Option A: load this repo directly (if fused model is uploaded)
+MODEL_ID = "rudycaz/phi35-phish-mlx"
+
+model, tokenizer = load(MODEL_ID)
+
+prompt = """You are a security assistant. Classify the following email as PHISHING or LEGIT.
 
-prompt = "hello"
+EMAIL:
+Subject: Verify your account
+Body: Please click the link below to verify...
 
-if tokenizer.chat_template is not None:
-    messages = [{"role": "user", "content": prompt}]
-    prompt = tokenizer.apply_chat_template(
-        messages, add_generation_prompt=True, return_dict=False,
-    )
+Answer with exactly one word: PHISHING or LEGIT.
+"""
 
-response = generate(model, tokenizer, prompt=prompt, verbose=True)
-```
+print(generate(model, tokenizer, prompt, max_tokens=8))