import os import urllib.request import gradio as gr from llama_cpp import Llama def download_file(file_link, filename): # Checks if the file already exists before downloading if not os.path.isfile(filename): urllib.request.urlretrieve(file_link, filename) print("File downloaded successfully.") else: print("File already exists.") # Dowloading GGML model from HuggingFace ggml_model_path = "https://huggingface.co/TheBloke/Starling-LM-7B-alpha-GGUF/resolve/main/starling-lm-7b-alpha.Q4_K_S.gguf" filename = "starling-lm-7b-alpha.Q4_K_S.gguf" download_file(ggml_model_path, filename) llm = Llama(model_path=filename, n_ctx=512, n_batch=126) def create_prompt(text): prompt = f"""GPT4 Correct User: {text}<|end_of_turn|>GPT4 Correct Assistant:""" return prompt def generate_text(prompt="Who is the CEO of Apple?"): input_text = create_prompt(prompt) output = llm( input_text, max_tokens=256, temperature=0.1, top_p=0.5, echo=False, stop=["#"], ) output_text = output["choices"][0]["text"].strip() # Remove Prompt Echo from Generated Text cleaned_output_text = output_text.replace(prompt, "") return cleaned_output_text description = "Starling-7B GGUF" gradio_interface = gr.Interface( fn=generate_text, inputs="text", outputs="text", title="Starling-7B GGUF", ) gradio_interface.launch()