Instructions to use MetaIX/OpenAssistant-Llama-30b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MetaIX/OpenAssistant-Llama-30b-4bit with Transformers:

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

pipe = pipeline("text-generation", model="MetaIX/OpenAssistant-Llama-30b-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MetaIX/OpenAssistant-Llama-30b-4bit")
model = AutoModelForCausalLM.from_pretrained("MetaIX/OpenAssistant-Llama-30b-4bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MetaIX/OpenAssistant-Llama-30b-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MetaIX/OpenAssistant-Llama-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/OpenAssistant-Llama-30b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MetaIX/OpenAssistant-Llama-30b-4bit

SGLang

How to use MetaIX/OpenAssistant-Llama-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/OpenAssistant-Llama-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/OpenAssistant-Llama-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/OpenAssistant-Llama-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/OpenAssistant-Llama-30b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MetaIX/OpenAssistant-Llama-30b-4bit with Docker Model Runner:
```
docker model run hf.co/MetaIX/OpenAssistant-Llama-30b-4bit
```

Works fine with llama.cpp / kobold.cpp!

by artemcrum - opened Apr 23, 2023

Discussion

artemcrum

Apr 23, 2023

Thank you! Model generates answers quite similar to what I get on https://open-assistant.io/chat/.

Remember to use markers:
<|prompter|>:
<|assistant|>:

Dezmo

May 19, 2023

When I asked this model --- "Generate a script for a new Fallout game. Come up with a new character and his story. Let the action take place in New York City. Come up with 4 different factions. Describe their morals and goals. Come up with an original plot that includes several complex moral choices of the main character when interacting with each of the factions. Outline several endings of the game, which ultimately have different effects on the factions." ---- the model started it very well, but then it wrote ".. sorry, I can't complete the task"

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