Instructions to use LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123 with Transformers:

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

pipe = pipeline("text-generation", model="LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123")
model = AutoModelForCausalLM.from_pretrained("LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123

SGLang

How to use LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123 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 "LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123" \
    --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": "LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123",
		"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 "LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123" \
        --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": "LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123 with Docker Model Runner:
```
docker model run hf.co/LyraNovaHeart/Dazzling-Star-Aurora-70b-v0.0-Experimental-0123
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Dazzling-Star-Aurora-70b-v0.0

If somewhere amid that aimlessly drifting sky, There was a planet where our wishes could flow free... would we try to make it there? I wonder what we'd wish for if we did...~

Listen to the song on youtube: https://www.youtube.com/watch?v=e1EExQiRhC0

70b version of Dazzling Star Aurora, with EVA L3.3 70b and RPMax L3.1 70b.

Models:

EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.3
unsloth/Meta-Llama-3.1-70B

Instruct Format: LLama 3

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using unsloth/Meta-Llama-3.1-70B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
    parameters:
      weight: 0.3
      density: 0.7
  - model: ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.3
    parameters:
      weight: 0.4
      density: 0.8
base_model: unsloth/Meta-Llama-3.1-70B
parameters:
  epsilon: 0.05
  lambda: 1
  normalize: true
  int8_mask: true
merge_method: ties
dtype: bfloat16