license, language, tags, pipeline_tag, base_model, datasets
license language tags pipeline_tag base_model datasets
apache-2.0
zh
qwen
text-generation
short-drama
lora
finetune
text-generation
Qwen/Qwen3-4B-Instruct-2507
EugeneMeng/Hongguo-Short-Drama-Corpus-AI-Labeled

Short-Drama-Title-Generator-4B (微短剧爆款剧名生成大模型)

中文介绍 | English Introduction

🎬 模型介绍

Short-Drama-Title-Generator-4B 是一款基于 Qwen3-4B-Instruct 深度微调的“微短剧爆款剧名生成器”。

本模型使用了高达 20,205 条真实的爆款微短剧数据集涵盖女频、男频、战神、甜宠、穿书、系统、打脸虐渣等全品类进行指令微调SFT。模型深谙下沉市场用户的心理与短剧“网感”能够根据简单的剧情简介和标签一键生成极具爽感、能引发病毒式传播的微短剧剧名。

核心应用场景

  • 短剧编剧/导演快速起名
  • 网文小说作者灵感激发
  • 短视频信息流广告素材起标题

🚀 快速开始 (Quick Start)

1. 依赖安装

pip install transformers accelerate vllm

2. Python 推理示例

我们推荐使用 transformers 库进行快速调用。请确保你遵循了训练时的 Prompt 格式(即包含【标签】和【简介】)。

from transformers import AutoModelForCausalLM, AutoTokenizer


model_name = "EugeneMeng/Short-Drama-Title-Generator-4B" 

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto")

# 你的指令和输入
instruction = "你是一名深谙下沉市场心理的顶级微短剧编剧。请根据以下剧情简介,为这部【女频】短剧起一个极具爽感、能引发病毒式传播的爆款剧名。"
input_text = "【标签】[\"都市爱情\", \"追妻火葬场\", \"打脸虐渣\"]\n【简介】林湘看清自己不过是父亲用来挽救公司、被塞进豪门的“工具人”。三年协议婚姻,她忍下冷暴力与流言。幡然醒悟后,她踢走势利保姆,重返职场,活成了前夫高攀不起的模样。"

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": f"{instruction}\n{input_text}"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# 生成剧名
generated_ids = model.generate(**model_inputs, max_new_tokens=50, temperature=0.7)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print("生成的剧名:", response)

3. Ollama 本地运行

文件包含Modelfile`,如果你熟悉 Ollama 生态,可以直接将其转换为 GGUF 并进行极其方便的本地部署调用。


🎬 Model Description (English)

Short-Drama-Title-Generator-4B is a specialized Large Language Model fine-tuned on the Qwen3-4B-Instruct architecture. It is designed to generate highly engaging, viral, and click-worthy titles for Chinese Short Dramas (微短剧).

The model was meticulously fine-tuned on a high-quality dataset containing 20,205 real-world popular short drama titles and plots. It excels at extracting core elements from a brief plot summary and outputting titles that strongly appeal to target audiences in the short video ecosystem.

⚠️ 免责声明 (Disclaimer)

本模型生成的剧名仅供参考,生成结果受输入文本和模型生成随机性影响。请用户在使用时遵守相关法律法规,不得用于生成、传播任何违法违规或侵犯他人权益的内容。

Description
Model synced from source: EugeneMeng/Short-Drama-Title-Generator-4B
Readme 30 KiB
Languages
Jinja 100%