from transformers import AutoTokenizer, AutoModelForCausalLMimport torch model_id = "prithivMLmods/Qwen3.5-9B-DS-v4-Flash-uncensored-heretic" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype="auto", device_map="auto") messages = [ { "role": "user", "content": "Explain how a transformer model processes text." }] inputs = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device) outputs = model.generate( inputs, max_new_tokens=512, temperature=0.7, top_p=0.9, do_sample=True) print( tokenizer.decode( outputs[0][inputs.shape[-1]:], skip_special_tokens=True ))