Instructions to use SteelStorage/ML-MS-Etheris-123B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SteelStorage/ML-MS-Etheris-123B with Transformers:

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

pipe = pipeline("text-generation", model="SteelStorage/ML-MS-Etheris-123B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SteelStorage/ML-MS-Etheris-123B")
model = AutoModelForCausalLM.from_pretrained("SteelStorage/ML-MS-Etheris-123B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SteelStorage/ML-MS-Etheris-123B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SteelStorage/ML-MS-Etheris-123B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SteelStorage/ML-MS-Etheris-123B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SteelStorage/ML-MS-Etheris-123B

SGLang

How to use SteelStorage/ML-MS-Etheris-123B 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 "SteelStorage/ML-MS-Etheris-123B" \
    --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": "SteelStorage/ML-MS-Etheris-123B",
		"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 "SteelStorage/ML-MS-Etheris-123B" \
        --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": "SteelStorage/ML-MS-Etheris-123B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SteelStorage/ML-MS-Etheris-123B with Docker Model Runner:
```
docker model run hf.co/SteelStorage/ML-MS-Etheris-123B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Now the cute anime girl has your attention

Creator: SteelSkull

About Etheris-123B:

Name Legend:
ML = Mistral-Large
MS = Model Stock
123B = its 123B

This model merges the robust storytelling of mutiple models while attempting to maintain intelligence. The final model was merged after Model Soup with DELLA to add some specal sause.

Use Mistral, ChatML, or Meth Format

Quants:

GGUF Quant: Mradermacher-GGUF

i1-GGUF Quant: Mradermacher-i1-GGUF

Config:

MODEL_NAME = "ML-MS-Etheris-123B" base_model: SillyTilly/Mistral-Large-Instruct-2407 merge_method: model_stock dtype: bfloat16 models: - model: NeverSleep/Lumimaid-v0.2-123B - model: TheDrummer/Behemoth-123B-v1 - model: migtissera/Tess-3-Mistral-Large-2-123B - model: anthracite-org/magnum-v2-123b

base_model: SillyTilly/Mistral-Large-Instruct-2407 merge_method: della dtype: bfloat16 models: -model: ./merge/msbase/Etheris-123B -model: ./merge/della/attempt3/model

If you wish to support:

Downloads last month: 5

Safetensors

Model size

123B params

Tensor type

BF16

Model tree for SteelStorage/ML-MS-Etheris-123B

NeverSleep/Lumimaid-v0.2-123B

SillyTilly/Mistral-Large-Instruct-2407

TheDrummer/Behemoth-123B-v1

anthracite-org/magnum-v2-123b

migtissera/Tess-3-Mistral-Large-2-123B

Merge model

this model

Quantizations

3 models