import gradio as gr import requests import os ##Bloom API_URL = "https://api-inference.huggingface.co/models/bigscience/bloom" HF_TOKEN = os.environ["HF_TOKEN"] headers = {"Authorization": f"Bearer {HF_TOKEN}"} def text_generate(prompt): print(f"*****Inside TEXT_generate - Prompt is :{prompt}") print(f"length of prompt is {len(prompt)}") json_ = {"inputs": prompt, "parameters": { "top_p": 0.9, "temperature": 1.1, "max_new_tokens": 250, "return_full_text": True, "do_sample":True, }, "options": {"use_cache": True, "wait_for_model": True, },} response = requests.post(API_URL, headers=headers, json=json_) print(f"Response is : {response}") output = response.json() print(f"output is : {output}") output_tmp = output[0]['generated_text'] print(f"output_tmp is: {output_tmp}") solution = output_tmp.split("\nQ:")[0] print(f"Final response after splits is: {solution}") if '\nOutput:' in solution: final_solution = solution.split("\nOutput:")[0] print(f"Response after removing output is: {final_solution}") elif '\n\n' in solution: final_solution = solution.split("\n\n")[0] print(f"Response after removing new line entries is: {final_solution}") else: final_solution = solution return final_solution demo = gr.Blocks() with demo: gr.Markdown("