Instructions to use xmj2002/gpt2_tang_poetry with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xmj2002/gpt2_tang_poetry with Transformers:

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

pipe = pipeline("text-generation", model="xmj2002/gpt2_tang_poetry")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xmj2002/gpt2_tang_poetry")
model = AutoModelForCausalLM.from_pretrained("xmj2002/gpt2_tang_poetry", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xmj2002/gpt2_tang_poetry with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xmj2002/gpt2_tang_poetry"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xmj2002/gpt2_tang_poetry",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/xmj2002/gpt2_tang_poetry

SGLang

How to use xmj2002/gpt2_tang_poetry 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 "xmj2002/gpt2_tang_poetry" \
    --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": "xmj2002/gpt2_tang_poetry",
		"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 "xmj2002/gpt2_tang_poetry" \
        --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": "xmj2002/gpt2_tang_poetry",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use xmj2002/gpt2_tang_poetry with Docker Model Runner:
```
docker model run hf.co/xmj2002/gpt2_tang_poetry
```

使用的预训练模型为uer/gpt2-chinese-cluecorpussmall

Usage

from transformers import AutoModelForCausalLM
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("xmj2002/gpt2_tang_poetry")
model = AutoModelForCausalLM.from_pretrained("xmj2002/gpt2_tang_poetry")

text = "白居易《远方》"
inputs = tokenizer(text, return_tensors="pt").input_ids
outputs = model.generate(inputs, max_new_tokens=100, do_sample=True, top_k=100, top_p=0.95)
tokenizer.decode(outputs[0], skip_special_tokens=True)

Downloads last month: 6

xmj2002
/

gpt2_tang_poetry

Usage

Dataset used to train xmj2002/gpt2_tang_poetry