Instructions to use royallab/Aetheria-L2-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use royallab/Aetheria-L2-70B with Transformers:

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

pipe = pipeline("text-generation", model="royallab/Aetheria-L2-70B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("royallab/Aetheria-L2-70B")
model = AutoModelForCausalLM.from_pretrained("royallab/Aetheria-L2-70B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use royallab/Aetheria-L2-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "royallab/Aetheria-L2-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "royallab/Aetheria-L2-70B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/royallab/Aetheria-L2-70B

SGLang

How to use royallab/Aetheria-L2-70B 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 "royallab/Aetheria-L2-70B" \
    --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": "royallab/Aetheria-L2-70B",
		"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 "royallab/Aetheria-L2-70B" \
        --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": "royallab/Aetheria-L2-70B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use royallab/Aetheria-L2-70B with Docker Model Runner:
```
docker model run hf.co/royallab/Aetheria-L2-70B
```

Prompting: limarp vs GOAT

by tachyphylaxis - opened Nov 30, 2023

Discussion

tachyphylaxis

Nov 30, 2023

Hello. I'm wondering if you've tested this with the GOAT model's storytelling prompt format, or even if you've used both at the same time, or some sort of chimerical prompt. Merging limarpv3 with that model is an intriguing idea. I haven't actually tried GOAT's accompanying code on github, have you? If so, did you try it with this model? Just curious.

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