Instructions to use TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ

SGLang

How to use TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ 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 "TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ" \
    --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": "TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ",
		"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 "TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ" \
        --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": "TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/GPlatty-30B-SuperHOT-8K-GPTQ
```

In text-generation-webui I don't see where to set the LOADER to ExLlama

by cleverest - opened Jun 29, 2023

Discussion

cleverest

Jun 29, 2023

What loader? Where is that selection even at? Do I need to install ExLlama in some way first to choose this? Thank you.

TheBloke

Owner Jun 29, 2023

It's on the Model page in text-generation-webui - see Step 1: "Click the Model tab"

If you are using the text-generation-webui one-click-installer then ExLlama should already be installed for you. If not, select it in the UI and there will be a link to click for manual install instructions.

cleverest

Jul 1, 2023

I had to reinstall text-generation-webui to get the latest version with the loader menu. It's all good now! Thanks!

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