Instructions to use aihijo/transformers4ime-pinyingpt-concat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aihijo/transformers4ime-pinyingpt-concat with Transformers:

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

pipe = pipeline("text-generation", model="aihijo/transformers4ime-pinyingpt-concat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aihijo/transformers4ime-pinyingpt-concat")
model = AutoModelForCausalLM.from_pretrained("aihijo/transformers4ime-pinyingpt-concat", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aihijo/transformers4ime-pinyingpt-concat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aihijo/transformers4ime-pinyingpt-concat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aihijo/transformers4ime-pinyingpt-concat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aihijo/transformers4ime-pinyingpt-concat

SGLang

How to use aihijo/transformers4ime-pinyingpt-concat 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 "aihijo/transformers4ime-pinyingpt-concat" \
    --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": "aihijo/transformers4ime-pinyingpt-concat",
		"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 "aihijo/transformers4ime-pinyingpt-concat" \
        --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": "aihijo/transformers4ime-pinyingpt-concat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aihijo/transformers4ime-pinyingpt-concat with Docker Model Runner:
```
docker model run hf.co/aihijo/transformers4ime-pinyingpt-concat
```

Transformers4IME

Transformers4IME is repo for exploring and adapting transformer-based models to IME.

PinyinGPT

PinyinGPT is a model from Exploring and Adapting Chinese GPT to Pinyin Input Method which appears in ACL2022.

@article{tan2022exploring,
  title={Exploring and Adapting Chinese GPT to Pinyin Input Method},
  author={Tan, Minghuan and Dai, Yong and Tang, Duyu and Feng, Zhangyin and Huang, Guoping and Jiang, Jing and Li, Jiwei and Shi, Shuming},
  journal={arXiv preprint arXiv:2203.00249},
  year={2022}
}

The code can be found at

Gitee
Github

Downloads last month: 34

Paper for aihijo/transformers4ime-pinyingpt-concat

Exploring and Adapting Chinese GPT to Pinyin Input Method

Paper • 2203.00249 • Published Mar 1, 2022