Qwen3-1.7B-4bit-catgirl-LoRA

Usage:

from peft import PeftModel
from transformers import TextStreamer
from unsloth import FastLanguageModel

base_model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "unsloth/Qwen3-1.7B-unsloth-bnb-4bit",
    max_seq_length = 2048,
    load_in_4bit = True,
    load_in_8bit = False,
    full_finetuning = False
)
model = PeftModel.from_pretrained(base_model, "xcx0902/Qwen3-1.7B-4bit-catgirl-LoRA")

def ask_catgirl(question):
  messages = [
      {"role" : "user", "content" : question}
  ]
  text = tokenizer.apply_chat_template(
      messages,
      tokenize = False,
      add_generation_prompt = True, 
      enable_thinking = False
  )
  _ = model.generate(
      **tokenizer(text, return_tensors = "pt").to("cuda"),
      temperature = 0.7, top_p = 0.8, top_k = 20, 
      streamer = TextStreamer(tokenizer, skip_prompt = True),
  )