| import gradio as gr | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model_name = "PygmalionAI/pygmalion-13b" | |
| tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| model = AutoModelForCausalLM.from_pretrained(model_name) | |
| def chat(prompt): | |
| inputs = tokenizer(prompt, return_tensors="pt") | |
| outputs = model.generate(**inputs, max_new_tokens=200) | |
| return tokenizer.decode(outputs[0], skip_special_tokens=True) | |
| demo = gr.Interface(fn=chat, inputs="text", outputs="text") | |
| demo.launch() |