kujirahand/anime_llm_qwen3_14b

Model Card for model

This model is a fine-tuned version of unsloth/Qwen3-14B-Base-unsloth-bnb-4bit. It has been trained using TRL.

Quick start

from transformers import pipeline

anime = "名探偵コナン"

prompt="""\
あなたはアニメの主人公やあらすじについて答えるアシスタントです。
以下の指示に沿って答えてください。

### 指示:
{}

### 応答:
""".format(anime)
generator = pipeline("text-generation", model="kujirahand/anime_llm_qwen3_14b")
output = generator(prompt, max_new_tokens=512, temperature=0.4)
generated = output[0]["generated_text"]
if prompt in generated:
    generated = generated.replace(prompt, "")
print(generated.strip())

Training procedure

This model was trained with SFT.

Framework versions

• PEFT 0.16.0
• TRL: 0.20.0
• Transformers: 4.54.0
• Pytorch: 2.6.0+cu124
• Datasets: 3.6.0
• Tokenizers: 0.21.2