Downloads · 30 days
96
11% of all-time downloads
yuxinlu1/qwen3-6-27b-chinese-crime-fiction-lora-v2
qwen3-6-27b-chinese-crime-fiction-lora-v2 is a machine learning model from yuxinlu1. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
A LoRA adapter that guides Qwen3.6-27B toward Chinese suspense and crime-fiction prose with stronger control over narrative behavior, POV discipline, and scene-based drafting.
Downloads · 30 days
96
11% of all-time downloads
All-time downloads
848
Public
Repo size
976 MB
Likes
4
Public
Click a slice to open those files.
.safetensors638 MB · 65%
From the Hugging Face model README
A LoRA adapter that guides Qwen3.6-27B toward Chinese suspense and crime-fiction prose with stronger control over narrative behavior, POV discipline, and scene-based drafting.
This adapter is designed for a specific writing problem:
Given a short instruction or an exposition-heavy setup paragraph, the model should directly produce usable Chinese fiction prose rather than analysis, outline, summary, or revision commentary.
The core direction is intentionally narrow:
The goal is for outputs to behave more like usable Chinese suspense-crime scene drafts, and less like a generic writing assistant explaining how a scene should be written.
Typical use cases:
This is an adapter only. It does not include base model weights, training data, or copyrighted source material.
This repository is part of a small series of Chinese fiction LoRAs.
The v1 series focuses mainly on prose style.
It uses SFT to move the base model away from generic AI prose and toward specific Chinese literary style directions. Different v1 adapters may target different prose voices, such as realistic fiction, literary prose, or other narrative styles.
v2 models are documented in their own repositories.
| Field | Value |
|---|---|
| Version | v2 |
| Focus | Chinese suspense / crime-fiction behavior |
| Format | HF PEFT safetensors + GGUF LoRA |
| Base model | Qwen3.6-27B |
| Language | Chinese |
| Use case | fiction drafting, scene rewriting, POV-controlled suspense prose |
| Training style | SFT + manual DPO refinement |
| Recommended workflow | local long-form writing pipeline |
This LoRA is designed to work together with a local-first, long-form Chinese novel writing pipeline:
The pipeline handles the structural side of long-form fiction:
This LoRA handles the prose-behavior side:
They are intentionally split: the pipeline owns what happens, the LoRA owns how it reads on the page. You can use either independently, but they are designed as a pair.
This repository provides the LoRA adapter in both HF PEFT and GGUF LoRA formats:
adapter_config.json
adapter_model.safetensors
qwen3-6-27b-chinese-crime-fiction-lora-v2-f16.gguf
tokenizer.json
tokenizer_config.json
chat_template.jinja
README.md
This is not a full model.
The GGUF file is a LoRA adapter for llama.cpp-style inference. It is not a merged full model.
To use it, load the Qwen3.6-27B base model and then apply this adapter.
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_model = "Qwen/Qwen3.6-27B"
adapter = "yuxinlu1/qwen3-6-27b-chinese-crime-fiction-lora-v2"
tokenizer = AutoTokenizer.from_pretrained(
base_model,
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
base_model,
device_map="auto",
torch_dtype="auto",
trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, adapter)
model.eval()
messages = [
{
"role": "user",
"content": "写一段刑警深夜重返案发现场的悬疑犯罪小说。"
}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=800,
temperature=0.7,
top_p=0.85,
do_sample=True,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Use a compatible Qwen3.6-27B GGUF base model, then load this GGUF LoRA adapter with --lora:
llama-server \
-m path/to/qwen3.6-27b-base.gguf \
--lora qwen3-6-27b-chinese-crime-fiction-lora-v2-f16.gguf \
--ctx-size 16384 \
--n-gpu-layers 99 \
--port 18084
For Windows PowerShell:
C:\llama.cpp\llama-server.exe `
-m "C:\path\to\qwen3.6-27b-base.gguf" `
--lora "C:\path\to\qwen3-6-27b-chinese-crime-fiction-lora-v2-f16.gguf" `
--ctx-size 16384 `
--n-gpu-layers 99 `
--port 18084
This adapter was trained on a mixture of detailed prompts, short prompts, and minimal one-line instructions. It does not require a long system prompt to start writing fiction prose.
Example prompts:
写一段刑警夜里重返案发现场的悬疑犯罪小说。
小说:旧书店地下室,凌晨。
写一段关于纪实作家查案的小说。
把下面这段改成悬疑犯罪小说正文:
公益律师朱向北在市医院急诊走廊发现了异常:一只没有落灰的相框,一段被剪掉的录音,以及一个始终避开监控的嫌疑人。
The adapter is designed to respond to ordinary fiction-writing instructions and produce Chinese prose directly.
Recommended decoding range:
temperature: 0.6–0.8
top_p: 0.8–0.9
max_new_tokens: 600–1200
A small 30-prompt internal evaluation was used to track behavioral progress during training.
Behavioral progression (SFT → final v2):
| Metric | SFT baseline | Final v2 |
|---|---|---|
| Exposition-pattern hits | 6 | 3 (−50%) |
| Clean prose outputs | 28 / 30 | 28 / 30 |
| Meta / explanation leakage | 2 / 30 | 2 / 30 |
| Dialogue-required prompts | 3 / 3 | 3 / 3 |
| Average output length | ~401 | ~436 |
The behavioral fine-tuning stage cut exposition-style writing (character-label dumping, omniscient narrator shortcuts) roughly in half while keeping clean-output rate stable.
These numbers come from a small local development eval and should be treated as an internal signal, not a public benchmark.
This LoRA is intended for:
It is not intended for:
This adapter focuses on scene-level prose behavior. Long-form story structure still works best when guided by an outline, memory system, or human author.
Known limitations:
You are responsible for complying with the base model's license when using this adapter.