Instructions to use grayhacker91/gemma-7b-open-platypus-commercial with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grayhacker91/gemma-7b-open-platypus-commercial with Transformers:

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

pipe = pipeline("text-generation", model="grayhacker91/gemma-7b-open-platypus-commercial")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grayhacker91/gemma-7b-open-platypus-commercial")
model = AutoModelForCausalLM.from_pretrained("grayhacker91/gemma-7b-open-platypus-commercial", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use grayhacker91/gemma-7b-open-platypus-commercial with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grayhacker91/gemma-7b-open-platypus-commercial"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grayhacker91/gemma-7b-open-platypus-commercial",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grayhacker91/gemma-7b-open-platypus-commercial

SGLang

How to use grayhacker91/gemma-7b-open-platypus-commercial 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 "grayhacker91/gemma-7b-open-platypus-commercial" \
    --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": "grayhacker91/gemma-7b-open-platypus-commercial",
		"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 "grayhacker91/gemma-7b-open-platypus-commercial" \
        --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": "grayhacker91/gemma-7b-open-platypus-commercial",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grayhacker91/gemma-7b-open-platypus-commercial with Docker Model Runner:
```
docker model run hf.co/grayhacker91/gemma-7b-open-platypus-commercial
```

gemma-7b-open-platypus-commercial

Model Details

Base Model

google/gemma-7b (https://huggingface.co/google/gemma-7b)

Training Dataset

kyujinpy/Open-platypus-Commercial (https://huggingface.co/datasets/kyujinpy/Open-platypus-Commercial)

Implementation Code

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "grayhacker91/gemma-7b-open-platypus-commercial"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)

Downloads last month: 6

Safetensors

Model size

9B params

Tensor type

F16

Model tree for grayhacker91/gemma-7b-open-platypus-commercial

Base model

google/gemma-7b

Finetuned

(367)

this model

grayhacker91
/

gemma-7b-open-platypus-commercial

gemma-7b-open-platypus-commercial

Model Details

Implementation Code

Model tree for grayhacker91/gemma-7b-open-platypus-commercial

Dataset used to train grayhacker91/gemma-7b-open-platypus-commercial