Instructions to use sylviali/eracond_llama_2_grammar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sylviali/eracond_llama_2_grammar with Transformers:

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

pipe = pipeline("text-generation", model="sylviali/eracond_llama_2_grammar")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sylviali/eracond_llama_2_grammar")
model = AutoModelForCausalLM.from_pretrained("sylviali/eracond_llama_2_grammar")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sylviali/eracond_llama_2_grammar with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sylviali/eracond_llama_2_grammar"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sylviali/eracond_llama_2_grammar",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sylviali/eracond_llama_2_grammar

SGLang

How to use sylviali/eracond_llama_2_grammar 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 "sylviali/eracond_llama_2_grammar" \
    --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": "sylviali/eracond_llama_2_grammar",
		"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 "sylviali/eracond_llama_2_grammar" \
        --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": "sylviali/eracond_llama_2_grammar",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sylviali/eracond_llama_2_grammar with Docker Model Runner:
```
docker model run hf.co/sylviali/eracond_llama_2_grammar
```

Model Card for Model ID

Model Details

This model is a Llama-2-7b-chat-hf model trained on ErAConD data, which is a dataset for grammar corrections for written dialogue conversations. This model is presented in Using Adaptive Empathetic Responses for Teaching English. Please refer to the paper and the corresponding repository for training detaills.

Downloads last month: 2

Safetensors

Model size

7B params

Tensor type

F32

BF16