Instructions to use ingen51/DialoGPT-medium-GPT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ingen51/DialoGPT-medium-GPT4 with Transformers:

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

pipe = pipeline("text-generation", model="ingen51/DialoGPT-medium-GPT4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ingen51/DialoGPT-medium-GPT4")
model = AutoModelForCausalLM.from_pretrained("ingen51/DialoGPT-medium-GPT4")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ingen51/DialoGPT-medium-GPT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ingen51/DialoGPT-medium-GPT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ingen51/DialoGPT-medium-GPT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ingen51/DialoGPT-medium-GPT4

SGLang

How to use ingen51/DialoGPT-medium-GPT4 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 "ingen51/DialoGPT-medium-GPT4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ingen51/DialoGPT-medium-GPT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ingen51/DialoGPT-medium-GPT4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ingen51/DialoGPT-medium-GPT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ingen51/DialoGPT-medium-GPT4 with Docker Model Runner:
```
docker model run hf.co/ingen51/DialoGPT-medium-GPT4
```

I'm new - need small direction

by Dude12345 - opened Apr 5, 2023

Discussion

Dude12345

Apr 5, 2023

If I want to run GPT4 locally what do I need to know about installing it. I don't need links, just give me the basic things I need to read up on so I can do it myself. Thank you!

ShreyasBrill

Apr 10, 2023

You can install oogabooga's Web UI in your PC and download this model, finally launch the Web UI and it should look like this!

There are tons of customisations that you can do here! you can try it out..

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