Instructions to use Sorihon/Celestial-Order-24B-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sorihon/Celestial-Order-24B-V2 with Transformers:

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

pipe = pipeline("text-generation", model="Sorihon/Celestial-Order-24B-V2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sorihon/Celestial-Order-24B-V2")
model = AutoModelForCausalLM.from_pretrained("Sorihon/Celestial-Order-24B-V2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Sorihon/Celestial-Order-24B-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sorihon/Celestial-Order-24B-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sorihon/Celestial-Order-24B-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Sorihon/Celestial-Order-24B-V2

SGLang

How to use Sorihon/Celestial-Order-24B-V2 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 "Sorihon/Celestial-Order-24B-V2" \
    --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": "Sorihon/Celestial-Order-24B-V2",
		"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 "Sorihon/Celestial-Order-24B-V2" \
        --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": "Sorihon/Celestial-Order-24B-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Sorihon/Celestial-Order-24B-V2 with Docker Model Runner:
```
docker model run hf.co/Sorihon/Celestial-Order-24B-V2
```

Quality merge

by redaihf - opened 15 days ago

Discussion

redaihf

15 days ago

•

edited 15 days ago

This is a stable merge that writes quality long-form content with ease. It retains some of the style from Morbid Miasma while resolving that model's rougher edges. Please consider including a chat template with future merges so that GGUF quants are ready to use out of the box so to speak. Example

redaihf

13 days ago

I have paired this model with an SRP Master Prompt. This delivers quality close to Cydonia 4.3. It has a bit less raw knowledge than Cydonia 4.3 but greater style and flair without so many Mistralisms. Bravo.

Sorihon

Owner 3 days ago

•

edited 3 days ago

I am glad that it worked out, when I saw Morbid Miasma I decided to test it out and within three responses I knew that it was the missing piece that I needed to make this merge, and I luckily got these results after a few failed attempts. Unfortunately it also took my PC with it so I couldn't test it much myself.

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