GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Xx-Vexento-xX
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Xx-Vexento-xX
Model Tree
unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit
Input Modalities
Output Modalities
Supported Functionality
python
import requests API_URL = "https://api-inference.huggingface.co/models/Xx-Vexento-xX/roast-bot-qwen-1b"headers = {"Authorization": "Bearer YOUR_HF_TOKEN"} prompt = "<|im_start|>systemYou are an AI agent trained on Sarvin's text style.<|im_end|><|im_start|>userbro ur actually dumb<|im_end|><|im_start|>assistant" response = requests.post(API_URL, headers=headers, json={ "inputs": prompt, "parameters": {"max_new_tokens": 100, "temperature": 0.75}})print(response.json()[0]["generated_text"])See the GitHub repo for the full WhatsApp agent harness that connects this model to WhatsApp.