Instructions to use qingy2024/GRMR-2B-Instruct-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qingy2024/GRMR-2B-Instruct-v2 with Transformers:

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

pipe = pipeline("text-generation", model="qingy2024/GRMR-2B-Instruct-v2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qingy2024/GRMR-2B-Instruct-v2")
model = AutoModelForCausalLM.from_pretrained("qingy2024/GRMR-2B-Instruct-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use qingy2024/GRMR-2B-Instruct-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qingy2024/GRMR-2B-Instruct-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qingy2024/GRMR-2B-Instruct-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/qingy2024/GRMR-2B-Instruct-v2

SGLang

How to use qingy2024/GRMR-2B-Instruct-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 "qingy2024/GRMR-2B-Instruct-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": "qingy2024/GRMR-2B-Instruct-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 "qingy2024/GRMR-2B-Instruct-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": "qingy2024/GRMR-2B-Instruct-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use qingy2024/GRMR-2B-Instruct-v2 with Docker Model Runner:
```
docker model run hf.co/qingy2024/GRMR-2B-Instruct-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Uploaded model

Developed by: qingy2024
License: apache-2.0
Finetuned from model : unsloth/gemma-2-2b-bnb-4bit

Fine tuned for a full epoch on qingy2024/grmr-20k

This fine-tune of Gemma 2 2B is trained to take any input text and repeat it (with fixed grammar).

Example:

User: Find a clip from a professional production of any musical within the past 50 years. The Tony awards have a lot of great options of performances of Tony nominated performances in the archives on their websites.

GRMR-2B-Instruct: Find a clip from a professional production of any musical within the past 50 years. The Tony Awards have a lot of great options of performances of Tony-nominated performances in their archives on their websites.

Note: This model uses a custom chat template:

Below is the original text. Please rewrite it to correct any grammatical errors if any, improve clarity, and enhance overall readability.

### Original Text:
{PROMPT HERE}

### Corrected Text:
{MODEL'S OUTPUT HERE}

I would recommend a temperature of 0.0 and repeat penalty 1.0 for this model to get optimal results.

Disclaimer, I ran this text through the model itself to correct the grammar.