Instructions to use SteelStorage/G2-MS-Nyxora-27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SteelStorage/G2-MS-Nyxora-27b with Transformers:

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

pipe = pipeline("text-generation", model="SteelStorage/G2-MS-Nyxora-27b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SteelStorage/G2-MS-Nyxora-27b")
model = AutoModelForCausalLM.from_pretrained("SteelStorage/G2-MS-Nyxora-27b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SteelStorage/G2-MS-Nyxora-27b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SteelStorage/G2-MS-Nyxora-27b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SteelStorage/G2-MS-Nyxora-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SteelStorage/G2-MS-Nyxora-27b

SGLang

How to use SteelStorage/G2-MS-Nyxora-27b 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/G2-MS-Nyxora-27b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SteelStorage/G2-MS-Nyxora-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/G2-MS-Nyxora-27b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SteelStorage/G2-MS-Nyxora-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SteelStorage/G2-MS-Nyxora-27b with Docker Model Runner:
```
docker model run hf.co/SteelStorage/G2-MS-Nyxora-27b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Now that the cute anime girl has your attention.

Creator: SteelSkull

About G2-MS-Nyxora-27b:

Model Name Legend =
"G2 = Gemma 2"
"MS = Model_stock"

This model represents an experimental foray into 27b models. Feedback is welcome for further improvements.

G2-MS-Nyxora-27b combines multiple models' strengths to provide a versatile assistant for various tasks, including general use, storytelling, and roleplay (ERP & RP).

The Model seems to be on the prudish side from google's training but seems to be fixed with a good system prompt. (Provided in files)

The Model_stock merge method ensures the model remains focused, tailored, and high-quality.

Quants:

Will add as found or im notified of their creation (If you know of one create a discussion!)

Mradermacher, GGUF Quants

Mradermacher/G2-MS-Nyxora-27b-GGUF

Mradermacher/G2-MS-Nyxora-27b-i1-GGUF

SteelQuants, My Personal Quants

- G2-MS-Nyxora-27b-Q4_K_M-GGUF

- G2-MS-Nyxora-27b-Q6_K-GGUF

Config:

MODEL_NAME = "G2-MS-Nyxora-27b"
yaml_config = """
base_model: google/gemma-2-27b-it
merge_method: model_stock
dtype: bfloat16
models:
  - model: TheDrummer/Big-Tiger-Gemma-27B-v1
  - model: migtissera/Tess-v2.5-Gemma-2-27B-alpha
"""

Template:

<start_of_turn>user
{{ if .System }}{{ .System }} {{ end }}{{ .Prompt }}<end_of_turn>
<start_of_turn>model
{{ .Response }}<end_of_turn>

Source Model Details:

TheDrummer/Big-Tiger-Gemma-27B-v1:
A decensored version of the Gemma 27B model.

migtissera/Tess-v2.5-Gemma-2-27B-alpha:
The latest state-of-the-art model in the Tess series, Tess-v2.5.2, offers significant improvements in reasoning, coding, and mathematics. It ranks #1 on the MMLU benchmark among open weight models and outperforms several frontier closed models.

Gemma-2-27b-it:
A lightweight, state-of-the-art model from Google, well-suited for various text generation tasks. Its small size allows deployment in resource-limited environments, fostering AI innovation for all.

Merge Method Details:

Model_stock Uses some neat geometric properties of fine tuned models to compute good weights for linear interpolation.

I've had a few people ask about donations so here's a link:

Downloads last month: 4

Safetensors

Model size

28B params

Tensor type

BF16

Model tree for SteelStorage/G2-MS-Nyxora-27b

Quantizations

5 models