Instructions to use huyisme-005/grammar_error_corrector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huyisme-005/grammar_error_corrector with Transformers:

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

pipe = pipeline("text-generation", model="huyisme-005/grammar_error_corrector")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huyisme-005/grammar_error_corrector")
model = AutoModelForCausalLM.from_pretrained("huyisme-005/grammar_error_corrector")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use huyisme-005/grammar_error_corrector with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huyisme-005/grammar_error_corrector"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huyisme-005/grammar_error_corrector",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/huyisme-005/grammar_error_corrector

SGLang

How to use huyisme-005/grammar_error_corrector 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 "huyisme-005/grammar_error_corrector" \
    --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": "huyisme-005/grammar_error_corrector",
		"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 "huyisme-005/grammar_error_corrector" \
        --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": "huyisme-005/grammar_error_corrector",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use huyisme-005/grammar_error_corrector with Docker Model Runner:
```
docker model run hf.co/huyisme-005/grammar_error_corrector
```

gemma_noisy_zarma_finetune

This model is a fine-tuned version of google/gemma-3-270m on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.0806

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 28
eval_batch_size: 28
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2439	1.0	9643	1.6537
0.9003	2.0	19286	1.8666
0.696	3.0	28929	2.0806

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.1.1
Tokenizers 0.22.1

Downloads last month: -

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for huyisme-005/grammar_error_corrector

Base model

google/gemma-3-270m

Finetuned

(143)

this model