| import gradio as gr | |
| from llama_cpp import Llama | |
| llm = Llama(model_path="eachadea_ggml-vic7b-q4_0.bin", n_ctx=1024) | |
| def generate_text(input_text): | |
| output = llm(f"{input_text}", max_tokens=512, stop=["Q:", "\n", "#"], echo=False) | |
| return output['choices'][0]['text'] | |
| input_text = gr.inputs.Textbox(lines= 10, label="Enter your input text") | |
| output_text = gr.outputs.Textbox(label="Output text") | |
| gr.Interface(fn=generate_text, inputs=input_text, outputs=output_text, title="Vicuna GGML").launch() | |