GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
oke39
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
oke39
Model Tree
unsloth/llama-3-8b-Instruct-bnb-4bit
Input Modalities
Output Modalities
Supported Functionality
| Metric | Score | Description |
|---|---|---|
| Bandit Pass Rate | 88.0% | Percentage of fixes that pass the Bandit static analysis security tool. |
| BLEU Score | 69.27 | High structural similarity to human-expert security patches. |
You can use this model directly via the Hugging Face Inference API or load it locally.
python
import requests API_URL = "[https://api-inference.huggingface.co/models/oke39/llama3-8b-secure-code](https://api-inference.huggingface.co/models/oke39/llama3-8b-secure-code)"headers = {"Authorization": "Bearer YOUR_HF_TOKEN"} payload = { "inputs": """<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are Jack, a Secure Code Agent. Fix the security vulnerability in the provided code.<|eot_id|><|start_header_id|>user<|end_header_id|> def login(username, password): # Vulnerable SQL Injection query = "SELECT * FROM users WHERE username = '" + username + "' AND password = '" + password + "'" cursor.execute(query)<|eot_id|><|start_header_id|>assistant<|end_header_id|>"""} response = requests.post(API_URL, headers=headers, json=payload)print(response.json())This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
import requests API_URL = "[https://api-inference.huggingface.co/models/oke39/llama3-8b-secure-code](https://api-inference.huggingface.co/models/oke39/llama3-8b-secure-code)"headers = {"Authorization": "Bearer YOUR_HF_TOKEN"} payload = { "inputs": """<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are Jack, a Secure Code Agent. Fix the security vulnerability in the provided code.<|eot_id|><|start_header_id|>user<|end_header_id|> def login(username, password): # Vulnerable SQL Injection query = "SELECT * FROM users WHERE username = '" + username + "' AND password = '" + password + "'" cursor.execute(query)<|eot_id|><|start_header_id|>assistant<|end_header_id|>"""} response = requests.post(API_URL, headers=headers, json=payload)print(response.json())