Instructions to use MetaIX/GPT4-X-Alpaca-30B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MetaIX/GPT4-X-Alpaca-30B-4bit with Transformers:

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

pipe = pipeline("text-generation", model="MetaIX/GPT4-X-Alpaca-30B-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MetaIX/GPT4-X-Alpaca-30B-4bit")
model = AutoModelForCausalLM.from_pretrained("MetaIX/GPT4-X-Alpaca-30B-4bit")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MetaIX/GPT4-X-Alpaca-30B-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MetaIX/GPT4-X-Alpaca-30B-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MetaIX/GPT4-X-Alpaca-30B-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MetaIX/GPT4-X-Alpaca-30B-4bit

SGLang

How to use MetaIX/GPT4-X-Alpaca-30B-4bit 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 "MetaIX/GPT4-X-Alpaca-30B-4bit" \
    --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": "MetaIX/GPT4-X-Alpaca-30B-4bit",
		"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 "MetaIX/GPT4-X-Alpaca-30B-4bit" \
        --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": "MetaIX/GPT4-X-Alpaca-30B-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MetaIX/GPT4-X-Alpaca-30B-4bit with Docker Model Runner:
```
docker model run hf.co/MetaIX/GPT4-X-Alpaca-30B-4bit
```

What model_type to set between "None" and "llama"? And what prompt style to use? There are plenty of the latter in Ooba's TextGenWebUI as of now and I'm pretty much lost (see pics for clarification)

#10

by sneedingface - opened May 13, 2023

Discussion

sneedingface

May 13, 2023

Also if these infos are generally available somewhere in the config files of the repo and I can find them autonomously please let me know so I won't bother you all ever again with these noob-ish questions, thank you!

MetaIX

Owner May 15, 2023

Use llama for model type and alpaca for prompt style.

sneedingface

May 15, 2023

•

edited May 15, 2023

Also if these infos are generally available somewhere in the config files of the repo and I can find them autonomously please let me know so I won't bother you all ever again with these noob-ish questions, thank you!

@MetaIX I swear I don't want to bother you but I would really appreciate if you could reply to that, I'm trying to learn what I can. Thank you and sorry if I'm annoying

Latent-Dreamscape

May 21, 2023

I've discovered over the years that it is far more annoying to constantly apologize rather than just ask with confidence lol. :D
I hear ya tho, I also sometimes struggle to find the right settings and it can be frustrating when nobody wants to help

sneedingface

May 21, 2023

I've discovered over the years that it is far more annoying to constantly apologize rather than just ask with confidence lol. :D
I hear ya tho, I also sometimes struggle to find the right settings and it can be frustrating when nobody wants to help

Got it, now fuck off. How am I doing?

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