Instructions to use garage-bAInd/GPlatty-30B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use garage-bAInd/GPlatty-30B with Transformers:

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

pipe = pipeline("text-generation", model="garage-bAInd/GPlatty-30B")

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

tokenizer = AutoTokenizer.from_pretrained("garage-bAInd/GPlatty-30B")
model = AutoModelForCausalLM.from_pretrained("garage-bAInd/GPlatty-30B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use garage-bAInd/GPlatty-30B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "garage-bAInd/GPlatty-30B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "garage-bAInd/GPlatty-30B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/garage-bAInd/GPlatty-30B

SGLang

How to use garage-bAInd/GPlatty-30B 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 "garage-bAInd/GPlatty-30B" \
    --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": "garage-bAInd/GPlatty-30B",
		"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 "garage-bAInd/GPlatty-30B" \
        --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": "garage-bAInd/GPlatty-30B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use garage-bAInd/GPlatty-30B with Docker Model Runner:
```
docker model run hf.co/garage-bAInd/GPlatty-30B
```

Curious about model design

by surya-narayanan - opened Jul 19, 2023

Discussion

surya-narayanan

Jul 19, 2023

Hi,

How do you merge two models? It says on your model card that your model is the merge of llama and gpt. I'm curious how you do that?

Surya

dball

Jul 23, 2023

I am very curious, too. @lilloukas , did you merge the alpaca-lora-30b adapter into the Platypus-30B model?

arielnlee

garage-bAInd org Jan 3, 2024

We merge the alpaca lora adapter onto the Platypus-30B model using PEFTs merge_and_unload function. There's a file for this in the GitHub repo!

arielnlee changed discussion status to closed Jan 3, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment