from peft import PeftModel, PeftConfig
from unsloth import FastLanguageModel
import torch
max_seq_length = 4096 # Can increase for longer reasoning traces
lora_rank = 32 # Larger rank = smarter, but slower
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = “unsloth/Qwen3-4B-Instruct-2507”,
max_seq_length = max_seq_length,
load_in_4bit = True, # False for LoRA 16bit
#fast_inference = Tr, # Enable vLLM fast inference
#max_lora_rank = lora_rank,
#gpu_memory_utilization = 0.7, # Reduce if out of memory
)
model = PeftModel.from_pretrained(model,
“/kaggle/input/qwen3-4b-instruct-lora/Qwen3_(4B)-Instruct_lora_model”,
is_trainable=True # 
here
)
…
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn