Instructions to use qiangge2026/merged_qwen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qiangge2026/merged_qwen with Transformers:

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

pipe = pipeline("text-generation", model="qiangge2026/merged_qwen")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qiangge2026/merged_qwen")
model = AutoModelForCausalLM.from_pretrained("qiangge2026/merged_qwen", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use qiangge2026/merged_qwen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qiangge2026/merged_qwen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qiangge2026/merged_qwen",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qiangge2026/merged_qwen

SGLang

How to use qiangge2026/merged_qwen 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 "qiangge2026/merged_qwen" \
    --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": "qiangge2026/merged_qwen",
		"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 "qiangge2026/merged_qwen" \
        --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": "qiangge2026/merged_qwen",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use qiangge2026/merged_qwen with Docker Model Runner:
```
docker model run hf.co/qiangge2026/merged_qwen
```

Qwen2-0.5B 古诗词生成微调模型

这是一个基于 Qwen/Qwen2-0.5B 进行 LoRA 微调并合并后的古诗词生成模型。

模型介绍

本项目通过 LoRA (Low-Rank Adaptation) 技术，在少量古诗词数据集上对 Qwen2-0.5B 进行了微调，使其能够根据用户输入的主题（如“春天”、“夏天”等）生成对应风格的古诗词。

训练数据

数据集：自定义古诗词数据集（包含春夏秋冬等不同主题）。
训练轮次：50 Epochs。
最终训练损失：约 7.68。

使用方法

你可以使用 transformers 库直接加载此模型进行推理：

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "qiangge2026/merged_qwen"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

prompt = "用户：写一首关于春天的诗\n助手："
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=50, do_sample=True, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 283

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for qiangge2026/merged_qwen

Base model

Qwen/Qwen2-0.5B

Adapter

(562)

this model

qiangge2026
/

merged_qwen

Qwen2-0.5B 古诗词生成微调模型

模型介绍

训练数据

使用方法

Model tree for qiangge2026/merged_qwen

Space using qiangge2026/merged_qwen 1