import os import gradio as gr import torch from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline # Correct model ID is HuggingFaceTB/SmolLM3-3B MODEL_ID = "HuggingFaceTB/SmolLM3-3B" print(f"Loading {MODEL_ID}...") tokenizer = AutoTokenizer.from_pretrained(MODEL_ID) model = AutoModelForCausalLM.from_pretrained( MODEL_ID, torch_dtype=torch.float16, device_map="cpu", low_cpu_mem_usage=True, ) print("Model loaded!") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, temperature=0.7, do_sample=True, pad_token_id=tokenizer.eos_token_id, ) def chat_fn(message, history): messages = [] for human, assistant in history: messages.append({"role": "user", "content": human}) messages.append({"role": "assistant", "content": assistant}) messages.append({"role": "user", "content": message}) prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) outputs = pipe(prompt, return_full_text=False) response = outputs[0]["generated_text"] if prompt in response: response = response[len(prompt):] return response demo = gr.ChatInterface( fn=chat_fn, title="SmolLM3-3B Chat (CPU)", description="Running Hugging Face's SmolLM3-3B on Free CPU Tier Space", textbox=gr.Textbox(placeholder="Type your message here...", container=False, scale=7), ) if __name__ == "__main__": demo.launch(server_name="0.0.0.0", server_port=7860)