Taku-Yumilab/qwen3-1.7b-issa-haiku-standalone

Qwen3-1.7B Issa Haiku (Standalone, Merged)

This is a standalone, merged version of Taku-Yumilab/qwen3-1.7b-issa-haiku-lora. The LoRA adapter weights have been merged into the base Qwen/Qwen3-1.7B weights, so this model can be loaded directly without the peft library.

Intended Output Structure

1. 1.Japanese haiku (Kanji and Kana)
2. 2.Blank line
3. 3.English poetic translation (2-4 lines)

Usage Example

~~~python import torch from transformers import AutoModelForCausalLM, AutoTokenizer

modelid = "Taku-Yumilab/qwen3-1.7b-issa-haiku-standalone" tokenizer = AutoTokenizer.frompretrained(modelid) model = AutoModelForCausalLM.frompretrained(modelid, torchdtype=torch.float16, device_map="auto")

messages = [ {"role": "system", "content": "You're a bilingual haiku poet who writes haiku in Japanese and provides an English translation."}, {"role": "user", "content": "Compose a haiku about a dragonfly"} ]

prompt = tokenizer.applychattemplate(messages, tokenize=False, addgenerationprompt=True, enablethinking=False) inputs = tokenizer(prompt, returntensors="pt").to(model.device)

with torch.inferencemode(): outputs = model.generate(**inputs, maxnewtokens=128, temperature=0.7, topp=0.8, top_k=20)

print(tokenizer.decode(outputs[0][inputs.inputids.shape[-1]:], skipspecial_tokens=True)) ~~~

Training Summary

Fine-tuned via QLoRA (r=32, alpha=64) for 1 epoch on 10,820 bilingual Issa haiku examples, then merged into the base weights for standalone deployment.