Instructions to use Yuaz-Club/yuaz-mini-cheng-dx-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yuaz-Club/yuaz-mini-cheng-dx-1b with Transformers:

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

pipe = pipeline("text-generation", model="Yuaz-Club/yuaz-mini-cheng-dx-1b", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Yuaz-Club/yuaz-mini-cheng-dx-1b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Yuaz-Club/yuaz-mini-cheng-dx-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yuaz-Club/yuaz-mini-cheng-dx-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yuaz-Club/yuaz-mini-cheng-dx-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Yuaz-Club/yuaz-mini-cheng-dx-1b

SGLang

How to use Yuaz-Club/yuaz-mini-cheng-dx-1b 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 "Yuaz-Club/yuaz-mini-cheng-dx-1b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yuaz-Club/yuaz-mini-cheng-dx-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Yuaz-Club/yuaz-mini-cheng-dx-1b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yuaz-Club/yuaz-mini-cheng-dx-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Yuaz-Club/yuaz-mini-cheng-dx-1b with Docker Model Runner:
```
docker model run hf.co/Yuaz-Club/yuaz-mini-cheng-dx-1b
```

Yuaz-mini-Cheng DX 1B

从零训练的 972M 参数中文对话模型。基于 LCCC + NaturalConv 数据集。

使用方法

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "Yuaz-Club/yuaz-mini-cheng-dx-1b",
    trust_remote_code=True,
    torch_dtype=torch.float16
)
tokenizer = AutoTokenizer.from_pretrained("Yuaz-Club/yuaz-mini-cheng-dx-1b", trust_remote_code=True)

inputs = tokenizer("你好", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=60)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

模型参数

参数	值
参数量	972M
层数	28
隐藏层	1792
注意力头	28 (GQA 4:1, 7 KV heads)
FFN	4864 (SwiGLU)
词表	8192 (BPE)
位置编码	RoPE
训练数据	314 万对话

模型文件

文件	大小	格式
`pytorch_model.bin`	1.8 GB	FP16

Downloads last month: 9

Yuaz-Club
/

yuaz-mini-cheng-dx-1b

Yuaz-mini-Cheng DX 1B

使用方法

模型参数

模型文件

Space using Yuaz-Club/yuaz-mini-cheng-dx-1b 1