Instructions to use Cipher-AI/AutoCorrect-EN-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cipher-AI/AutoCorrect-EN-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Cipher-AI/AutoCorrect-EN-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Cipher-AI/AutoCorrect-EN-v2")
model = AutoModelForSeq2SeqLM.from_pretrained("Cipher-AI/AutoCorrect-EN-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Cipher-AI/AutoCorrect-EN-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Cipher-AI/AutoCorrect-EN-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cipher-AI/AutoCorrect-EN-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Cipher-AI/AutoCorrect-EN-v2

SGLang

How to use Cipher-AI/AutoCorrect-EN-v2 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 "Cipher-AI/AutoCorrect-EN-v2" \
    --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": "Cipher-AI/AutoCorrect-EN-v2",
		"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 "Cipher-AI/AutoCorrect-EN-v2" \
        --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": "Cipher-AI/AutoCorrect-EN-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Cipher-AI/AutoCorrect-EN-v2 with Docker Model Runner:
```
docker model run hf.co/Cipher-AI/AutoCorrect-EN-v2
```

suayptalha commited on Mar 13, 2025

Commit

0596bc8

verified ·

1 Parent(s): 3e24a1c

Update README.md

Browse files

Files changed (1) hide show

README.md +29 -3

README.md CHANGED Viewed

@@ -1,3 +1,29 @@
----
-license: apache-2.0
----

+---
+license: apache-2.0
+datasets:
+- agentlans/high-quality-english-sentences
+language:
+- en
+base_model:
+- google-t5/t5-base
+pipeline_tag: text2text-generation
+library_name: transformers
+---
+This model is for typos in texts and it outputs corrected texts.
+Example:
+Text with Typos: **Whathvhr wh call owr carhaivhrs - doctors, nwrsh practitionhrs, clinicians, - wh nhhd thhm not only to carh, wh nhhd thhm to uh aulh to providh thh riaht valwh.**
+Corrected Text: **Whatever we call our caregivers - doctors, nurse practitioners, clinicians, - we need them not only to care, we need them to be able to provide the right value.**
+Example Usage:
+```py
+#Load the model and tokenizer
+text = "" #Text with typos here!
+inputs = tokenizer(cipher_text, return_tensors="pt", padding=True, truncation=True, max_length=256).to(device)
+outputs = model.generate(inputs["input_ids"], max_length=256)
+corrected_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+```