import gradio as gr import spaces import torch from transformers import AutoProcessor, AutoModelForMultimodalLM MODEL_ID = "google/gemma-4-E4B-it" processor = AutoProcessor.from_pretrained(MODEL_ID) model = AutoModelForMultimodalLM.from_pretrained( MODEL_ID, dtype="auto", device_map="auto", ) @spaces.GPU def chat(message, history): messages = [] for user, assistant in history: messages.append({ "role": "user", "content": user }) messages.append({ "role": "assistant", "content": assistant }) messages.append({ "role": "user", "content": message }) inputs = processor.apply_chat_template( messages, tokenize=True, return_dict=True, return_tensors="pt", add_generation_prompt=True, enable_thinking=False, ).to(model.device) input_len = inputs["input_ids"].shape[-1] with torch.inference_mode(): outputs = model.generate( **inputs, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95, ) response = processor.decode( outputs[0][input_len:], skip_special_tokens=False ) response = processor.parse_response(response) return response demo = gr.ChatInterface( fn=chat, title="Gemma 4 E4B", textbox=gr.Textbox( placeholder="Напиши что-нибудь...", container=True ), ) demo.launch()