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

Libraries

How to use Ashishkr/grammar_correction with Transformers:

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

pipe = pipeline("text-generation", model="Ashishkr/grammar_correction")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ashishkr/grammar_correction")
model = AutoModelForCausalLM.from_pretrained("Ashishkr/grammar_correction")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ashishkr/grammar_correction with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Ashishkr/grammar_correction

SGLang

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

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

from transformers import AutoTokenizer, AutoModelWithLMHead, AutoModelForCausalLM
import torch
if torch.cuda.is_available():
    device = torch.device("cuda")
else :
    device = "cpu"


tokenizer = AutoTokenizer.from_pretrained("Ashishkr/grammar_correction")  
model = AutoModelForCausalLM.from_pretrained("Ashishkr/grammar_correction").to(device)

input_query="what be the reason for everyone leave the company"
query= "<|startoftext|> " + input_query + " ~~~"


input_ids = tokenizer.encode(query.lower(), return_tensors='pt').to(device)
sample_outputs = model.generate(input_ids,
                                do_sample=True,
                                num_beams=1, 
                                max_length=128,
                                temperature=0.9,
                                top_p= 0.7,
                                top_k = 5,
                                num_return_sequences=3)
corrected_sentences = []
for i in range(len(sample_outputs)):
    r = tokenizer.decode(sample_outputs[i], skip_special_tokens=True).split('||')[0]
    r = r.split('~~~')[1]
    if r not in corrected_sentences:
        corrected_sentences.append(r)

print(corrected_sentences)

Downloads last month: 20