Instructions to use shigureui/lightnovel_cpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shigureui/lightnovel_cpt with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="shigureui/lightnovel_cpt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shigureui/lightnovel_cpt")
model = AutoModelForCausalLM.from_pretrained("shigureui/lightnovel_cpt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use shigureui/lightnovel_cpt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shigureui/lightnovel_cpt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shigureui/lightnovel_cpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shigureui/lightnovel_cpt

SGLang

How to use shigureui/lightnovel_cpt with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "shigureui/lightnovel_cpt" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shigureui/lightnovel_cpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "shigureui/lightnovel_cpt" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shigureui/lightnovel_cpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shigureui/lightnovel_cpt with Docker Model Runner:
```
docker model run hf.co/shigureui/lightnovel_cpt
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

使用了Megatron CPT训练的轻小说大模型

使用了Pai Megatron + 32K Sequence Length + FP8 + H100 集群训练

这个模型是CPT版本。使用了32K为目标切分的小说，所以可以输入非常长的内容，不过int8量化的话我不好说（24G卡BF16 32K content windows, 杂鱼！）

关于数据

轻小说数据在7G左右，这个版本是CPT版本，没有SFT，请不要期待指令跟随。
Roleplay数据非常容易导致过拟合，增加猫箱的RP数据会导致小说的续写长度变短，并且没有发现anime girl效果变好。（几家app用户大多是同人女的关系？）
h-corpus质量参差不齐，只采样了一些，用了与轻小说数据量相同的7G左右的文本。（这个数据集与轻小说没有完全太重合，考虑pixiv子集）
SFT的数据没有准备好，涉及到summary文章再写作，还有给定章节续写，对话的RP依旧非常头痛。
h-corpus的summary暂时没有做，summary用的模型一时没有太好的选择。

轻小说数据来源包括 https://github.com/ixinzhi/lightnovel-2023 清洗脚本晚些可能公开

7B模型整体效果感觉马马虎虎，不过由于整体数据没有太被污染，效果明显。

已经训练好32B的模型（TP=8 FP8），32B版本逻辑性明显好。（搬到huggingface比较久）

如果模型载入有问题的话，请用qwen2.5原本的tokenizer、vocab等等覆盖一下，我只有权重的megatron转换出来的。

模型的翻译腔是预期效果？

Downloads last month: 11

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for shigureui/lightnovel_cpt

Base model

Qwen/Qwen2.5-7B

Finetuned

(960)

this model

Quantizations

2 models

shigureui
/

lightnovel_cpt

使用了Megatron CPT训练的轻小说大模型

关于数据

Model tree for shigureui/lightnovel_cpt

Dataset used to train shigureui/lightnovel_cpt