MetaIX
/

GPT4-X-Alpasta-30b

Text Generation

text-generation-inference

Model card Files Files and versions

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

Libraries

How to use MetaIX/GPT4-X-Alpasta-30b with Transformers:

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

pipe = pipeline("text-generation", model="MetaIX/GPT4-X-Alpasta-30b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MetaIX/GPT4-X-Alpasta-30b")
model = AutoModelForCausalLM.from_pretrained("MetaIX/GPT4-X-Alpasta-30b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use MetaIX/GPT4-X-Alpasta-30b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MetaIX/GPT4-X-Alpasta-30b"
# 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-Alpasta-30b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MetaIX/GPT4-X-Alpasta-30b

How to use MetaIX/GPT4-X-Alpasta-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 "MetaIX/GPT4-X-Alpasta-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": "MetaIX/GPT4-X-Alpasta-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 "MetaIX/GPT4-X-Alpasta-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": "MetaIX/GPT4-X-Alpasta-30b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MetaIX/GPT4-X-Alpasta-30b with Docker Model Runner:
```
docker model run hf.co/MetaIX/GPT4-X-Alpasta-30b
```

What is this?

#1

by vdruts - opened Apr 27, 2023

LOL. What is this based on?

Owner Apr 27, 2023

•

edited Apr 27, 2023

Owner Apr 28, 2023

Updated the model card with more info. Err.. apologies.

•

edited Apr 28, 2023

GPTQ 4bit planned?
edit: found it here
https://huggingface.co/Aeala/GPT4-x-AlpacaDente-30b-4bit

Hmm, can't seem to load it in Ooba with the latest GPTQ

Owner Apr 29, 2023

GPTQ 4bit planned?
edit: found it here
https://huggingface.co/Aeala/GPT4-x-AlpacaDente-30b-4bit

That's a different version. It's pretty good. I'll also upload 4bit shortly.

Owner Apr 29, 2023

Here you go. https://huggingface.co/MetaIX/GPT4-X-Alpasta-30b-4bit/tree/main Uploading 128g/ggml q4_1+2+3 soon

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