Instructions to use otelk/mt-error-detect-correct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use otelk/mt-error-detect-correct with Transformers:

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

pipe = pipeline("text-generation", model="otelk/mt-error-detect-correct")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("otelk/mt-error-detect-correct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use otelk/mt-error-detect-correct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/otelk/mt-error-detect-correct

SGLang

How to use otelk/mt-error-detect-correct 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 "otelk/mt-error-detect-correct" \
    --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": "otelk/mt-error-detect-correct",
		"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 "otelk/mt-error-detect-correct" \
        --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": "otelk/mt-error-detect-correct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use otelk/mt-error-detect-correct with Docker Model Runner:
```
docker model run hf.co/otelk/mt-error-detect-correct
```

otelk commited on 26 days ago

Commit

d540b7d

verified ·

1 Parent(s): 0004aa5

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -89,6 +89,4 @@ outputs = llm.generate(
     sampling_params=sampling_params,
     lora_request=lora_request
 )
-```
-For both tasks, the tokenizer is loaded from the corresponding `model` directory rather than the LoRA directory.

     sampling_params=sampling_params,
     lora_request=lora_request
 )
+```