import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # 1. Load base model and tokenizermodel_id = "Qwen/Qwen3-1.7B"tokenizer = AutoTokenizer.from_pretrained(model_id) base_model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto") # 2. Attach fine-tuned lipogram adaptermodel = PeftModel.from_pretrained(base_model, "prateekfr/qwen3-1.7b-no-e-lora")model.eval() # 3. Build forbidden token mask (blocking 'e' and 'E')vocab_size = model.config.vocab_sizeforbidden_mask = torch.zeros(vocab_size, dtype=torch.bool)for token_id in range(vocab_size): token_str = tokenizer.decode([token_id]) if "e" in token_str.lower(): forbidden_mask[token_id] = True # 4. Generate with mask applied to logitsprompt = "Write a short poem about a frog."inputs = tokenizer(f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n", return_tensors="pt").to("cuda") with torch.no_grad(): curr_ids = inputs["input_ids"] for _ in range(60): outputs = model(input_ids=curr_ids) scores = outputs.logits[:, -1, :].clone().float() scores[:, forbidden_mask.to("cuda")] = -float("inf") next_token = torch.multinomial((scores / 0.7).softmax(-1), num_samples=1) if next_token.item() == tokenizer.eos_token_id: break curr_ids = torch.cat([curr_ids, next_token], dim=-1) print(tokenizer.decode(curr_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True).strip())