Instructions to use shikunpunk/Qwen3.8-27B-LiBai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shikunpunk/Qwen3.8-27B-LiBai with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/root/models/Qwen3.8-27B")
model = PeftModel.from_pretrained(base_model, "shikunpunk/Qwen3.8-27B-LiBai")

Transformers

How to use shikunpunk/Qwen3.8-27B-LiBai with Transformers:

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

pipe = pipeline("text-generation", model="shikunpunk/Qwen3.8-27B-LiBai")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("shikunpunk/Qwen3.8-27B-LiBai", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use shikunpunk/Qwen3.8-27B-LiBai with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shikunpunk/Qwen3.8-27B-LiBai"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shikunpunk/Qwen3.8-27B-LiBai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shikunpunk/Qwen3.8-27B-LiBai

SGLang

How to use shikunpunk/Qwen3.8-27B-LiBai 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 "shikunpunk/Qwen3.8-27B-LiBai" \
    --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": "shikunpunk/Qwen3.8-27B-LiBai",
		"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 "shikunpunk/Qwen3.8-27B-LiBai" \
        --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": "shikunpunk/Qwen3.8-27B-LiBai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shikunpunk/Qwen3.8-27B-LiBai with Docker Model Runner:
```
docker model run hf.co/shikunpunk/Qwen3.8-27B-LiBai
```

Qwen3.8-27B LiBai LoRA Adapter（李白风格 SFT）

基于 Qwen/Qwen3.8-27B 的李白风格 QLoRA SFT adapter。

模型说明

基座模型：Qwen/Qwen3.8-27B（Qwen3_5 架构，多模态条件生成）
训练方法：QLoRA 4-bit SFT（NF4 + double quant，LoRA r=16, alpha=32, dropout=0.05）
训练数据：李白诗集 300 条（libai_train_300.jsonl，ShareGPT 格式：system=李白风格人设 + human=创作请求 + gpt=真实李白诗）
训练配置：4 epochs，max_len=768，batch=2，grad_accum=8，lr=2e-4
训练结果：train_loss 2.55 → 0.197（快速小规模版）

使用方法

from transformers import AutoModelForCausalLM, AutoProcessor, BitsAndBytesConfig
from peft import PeftModel
import torch

base = "Qwen/Qwen3.8-27B"
adapter = "shikunpunk/Qwen3.8-27B-LiBai"

quant = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16,
                           bnb_4bit_quant_type="nf4", bnb_4bit_use_double_quant=True)
model = AutoModelForCausalLM.from_pretrained(base, trust_remote_code=True,
                                             torch_dtype=torch.bfloat16, device_map="auto",
                                             quantization_config=quant)
model = PeftModel.from_pretrained(model, adapter, is_trainable=False)
processor = AutoProcessor.from_pretrained(base, trust_remote_code=True)
model.eval()

说明

该 adapter 用于李白风格诗歌生成；配合 KTO 后训练版本 shikunpunk/Qwen3.8-27B-LiBai-KTO 使用效果更佳。
数据与训练脚本见 GitHub：https://github.com/shikunpneg/ChineseHardJudgePoem
风格池：data/libai_train.jsonl（838 条）

许可证

MIT

Downloads last month: 16

Model tree for shikunpunk/Qwen3.8-27B-LiBai

Base model

Qwen/Qwen3.8-27B

Adapter

(44)

this model