Instructions to use CodeTed/Chinese_Spelling_Correction_T5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodeTed/Chinese_Spelling_Correction_T5 with Transformers:

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

pipe = pipeline("text-generation", model="CodeTed/Chinese_Spelling_Correction_T5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("CodeTed/Chinese_Spelling_Correction_T5")
model = AutoModelForSeq2SeqLM.from_pretrained("CodeTed/Chinese_Spelling_Correction_T5", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CodeTed/Chinese_Spelling_Correction_T5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CodeTed/Chinese_Spelling_Correction_T5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodeTed/Chinese_Spelling_Correction_T5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CodeTed/Chinese_Spelling_Correction_T5

SGLang

How to use CodeTed/Chinese_Spelling_Correction_T5 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 "CodeTed/Chinese_Spelling_Correction_T5" \
    --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": "CodeTed/Chinese_Spelling_Correction_T5",
		"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 "CodeTed/Chinese_Spelling_Correction_T5" \
        --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": "CodeTed/Chinese_Spelling_Correction_T5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CodeTed/Chinese_Spelling_Correction_T5 with Docker Model Runner:
```
docker model run hf.co/CodeTed/Chinese_Spelling_Correction_T5
```

CodeTed commited on Nov 14, 2023

Commit

394c1d1

1 Parent(s): 6f76bf8

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -0

README.md CHANGED Viewed

@@ -27,6 +27,19 @@ This model was obtained by `instruction-tuning` the corresponding `ClueAI/Prompt
 ### Model Sources
 - Repository: [https://github.com/TedYeh/Chinese_spelling_Correction](https://github.com/TedYeh/Chinese_spelling_Correction)
 ## Usage
 ```python
 from transformers import AutoTokenizer, T5ForConditionalGeneration

 ### Model Sources
 - Repository: [https://github.com/TedYeh/Chinese_spelling_Correction](https://github.com/TedYeh/Chinese_spelling_Correction)
+### Evaluation
+accuracy	recall	precision	F1	FPR
+- Chinese spelling error correction task(SIGHAN2015)：
+| Model           | Base Model                  | accuracy  |  recall   | precision | F1    | FPR   |
+|:--------------:|:---------------------------:|:---------:|:---------:|:---------:|:-----:|:-----:|
+| GECToR         | hfl/chinese-macbert-base    | 71.7     | 71.6 | 71.8 | 71.7  | 28.2 |
+| GECToR_large   | hfl/chinese-macbert-large   | 73.7     | 76.5 | 72.5 | 74.4 | 29.1 |
+| T5 w/ pretrain | ClueAI/PromptCLUE-base-v1-5 | 79.2     | 69.2 | 85.8 | 76.6 | 11.1 |
+| T5 w/o pretrain| ClueAI/PromptCLUE-base-v1-5 | 75.1     | 63.1 | 82.2 | 71.4 | 13.3 |
+| PTCSpell       |                             | N/A     | 79.0 | 89.4 | 83.8 | N/A |
+| MDCSpell       |                             | N/A     | 77.2 | 81.5 | 79.3 |  N/A |
 ## Usage
 ```python
 from transformers import AutoTokenizer, T5ForConditionalGeneration