Instructions to use Gryphe/LlamaGramma-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gryphe/LlamaGramma-7b with Transformers:

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

pipe = pipeline("text-generation", model="Gryphe/LlamaGramma-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gryphe/LlamaGramma-7b")
model = AutoModelForCausalLM.from_pretrained("Gryphe/LlamaGramma-7b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gryphe/LlamaGramma-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gryphe/LlamaGramma-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gryphe/LlamaGramma-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Gryphe/LlamaGramma-7b

SGLang

How to use Gryphe/LlamaGramma-7b 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 "Gryphe/LlamaGramma-7b" \
    --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": "Gryphe/LlamaGramma-7b",
		"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 "Gryphe/LlamaGramma-7b" \
        --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": "Gryphe/LlamaGramma-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Gryphe/LlamaGramma-7b with Docker Model Runner:
```
docker model run hf.co/Gryphe/LlamaGramma-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A full finetune of Llama 2 7B using my Alpaca-transformed CoEdIT dataset. I gave it three epochs of training using a single A100 80GB GPU.

The intent was to create a L2 model that specializes in grammar correction. Results may vary.

Prompt Format

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Remove all grammatical errors from this text: <insert text here>

### Response:

Downloads last month: 5

Model tree for Gryphe/LlamaGramma-7b

Quantizations

2 models

Gryphe
/

LlamaGramma-7b

Prompt Format

Model tree for Gryphe/LlamaGramma-7b

Dataset used to train Gryphe/LlamaGramma-7b