metadata
language:
- en
tags:
- text-generation
- llama
- instruct
license: apache-2.0
pipeline_tag: text-generation
LLaDA-8B-Instruct Model
This is the LLaDA-8B-Instruct model deployed as a Hugging Face inference endpoint.
Model Details
LLaDA-8B-Instruct is a language model designed for instruction-following tasks.
Usage
This model can be used for text generation tasks. Here's an example:
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
api_inference:
handler_class: handler.EndpointHandler