import requests

API_URL = "https://YOUR-ENDPOINT-URL"
headers = {"Authorization": "Bearer YOUR_HF_TOKEN"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

output = query({
    "inputs": "Write a short story about a robot learning to paint:",
    "parameters": {
        "max_new_tokens": 250,
        "temperature": 0.7,
        "top_p": 0.95,
        "do_sample": true
    }
})

API Inference Configuration

yaml

api_inference:
  handler_class: handler.EndpointHandler

CodyBontecou/llada-8b-instruct-endpoint

LLaDA-8B-Instruct Model

Model Details

Usage

API Inference Configuration

CodyBontecou/
llada-8b-instruct-endpoint