Instructions to use liam168/gen-gpt2-medium-chinese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liam168/gen-gpt2-medium-chinese with Transformers:

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

pipe = pipeline("text-generation", model="liam168/gen-gpt2-medium-chinese")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("liam168/gen-gpt2-medium-chinese")
model = AutoModelForCausalLM.from_pretrained("liam168/gen-gpt2-medium-chinese")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use liam168/gen-gpt2-medium-chinese with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liam168/gen-gpt2-medium-chinese"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liam168/gen-gpt2-medium-chinese",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liam168/gen-gpt2-medium-chinese

SGLang

How to use liam168/gen-gpt2-medium-chinese 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 "liam168/gen-gpt2-medium-chinese" \
    --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": "liam168/gen-gpt2-medium-chinese",
		"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 "liam168/gen-gpt2-medium-chinese" \
        --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": "liam168/gen-gpt2-medium-chinese",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liam168/gen-gpt2-medium-chinese with Docker Model Runner:
```
docker model run hf.co/liam168/gen-gpt2-medium-chinese
```

gen-gpt2-medium-chinese

Overview

Language model: GPT2-Medium
Model size: 68M
Language: Chinese

Example

from transformers import TFGPT2LMHeadModel,AutoTokenizer
from transformers import TextGenerationPipeline

mode_name = 'liam168/gen-gpt2-medium-chinese'
tokenizer = AutoTokenizer.from_pretrained(mode_name)
model = TFGPT2LMHeadModel.from_pretrained(mode_name)

text_generator = TextGenerationPipeline(model, tokenizer)

print(text_generator("晓日千红", max_length=64, do_sample=True))
print(text_generator("加餐小语", max_length=50, do_sample=False))

输出

[{'generated_text': '晓日千红 独 远 客 。 孤 夜 云 云 梦 到 冷 。 著 剩 笑 、 人 远 。 灯 啼 鸦 最 回 吟 。 望 ， 枕 付 孤 灯 、 客 。 对 梅 残 照 偏 相 思 ， 玉 弦 语 。 翠 台 新 妆 、 沉 、 登 临 水 。 空'}]
[{'generated_text': '加餐小语 有 有 骨 ， 有 人 诗 成 自 远 诗 。 死 了 自 喜 乐 ， 独 撑 天 下 诗 事 小 诗 柴 。 桃 花 谁 知 何 处 何 处 高 吟 诗 从 今 死 火 ， 此 事'}]

Downloads last month: 4