Instructions to use maicomputer/gpt4-x-alpaca with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maicomputer/gpt4-x-alpaca with Transformers:

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

pipe = pipeline("text-generation", model="maicomputer/gpt4-x-alpaca")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("maicomputer/gpt4-x-alpaca")
model = AutoModelForCausalLM.from_pretrained("maicomputer/gpt4-x-alpaca", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use maicomputer/gpt4-x-alpaca with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maicomputer/gpt4-x-alpaca"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maicomputer/gpt4-x-alpaca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/maicomputer/gpt4-x-alpaca

SGLang

How to use maicomputer/gpt4-x-alpaca 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 "maicomputer/gpt4-x-alpaca" \
    --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": "maicomputer/gpt4-x-alpaca",
		"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 "maicomputer/gpt4-x-alpaca" \
        --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": "maicomputer/gpt4-x-alpaca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use maicomputer/gpt4-x-alpaca with Docker Model Runner:
```
docker model run hf.co/maicomputer/gpt4-x-alpaca
```

fp16 version of the model

by Light4Bear - opened Apr 3, 2023

Discussion

Light4Bear

Apr 3, 2023

Is there any benefit using fp32? I think the original Llama from meta is already in fp16.

teknium

Apr 5, 2023

It will run in fp16 in transformers, but it would have been better to have fp16 uploaded so it would be smaller

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