Instructions to use SteelStorage/G2-DA-Nyxora-27b-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SteelStorage/G2-DA-Nyxora-27b-V2 with Transformers:

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

pipe = pipeline("text-generation", model="SteelStorage/G2-DA-Nyxora-27b-V2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SteelStorage/G2-DA-Nyxora-27b-V2")
model = AutoModelForCausalLM.from_pretrained("SteelStorage/G2-DA-Nyxora-27b-V2")
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-DA-Nyxora-27b-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SteelStorage/G2-DA-Nyxora-27b-V2"
# 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-DA-Nyxora-27b-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SteelStorage/G2-DA-Nyxora-27b-V2

SGLang

How to use SteelStorage/G2-DA-Nyxora-27b-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 "SteelStorage/G2-DA-Nyxora-27b-V2" \
    --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-DA-Nyxora-27b-V2",
		"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-DA-Nyxora-27b-V2" \
        --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-DA-Nyxora-27b-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SteelStorage/G2-DA-Nyxora-27b-V2 with Docker Model Runner:
```
docker model run hf.co/SteelStorage/G2-DA-Nyxora-27b-V2
```
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-DA-Nyxora-27b-V2:

Model Name Legend =
"G2 = Gemma 2"
"DA = Della"
"Nyxora = Tiger Base = cat = Nya"
"27b = its 27b"
"V2 = V2"

This model is the second experimental foray into 27b models. Feedback is welcome for further improvements.

G2-DA-Nyxora-27b-V2 combines multiple models' strengths to provide a versatile assistant for various tasks, including general use, storytelling, and roleplay (ERP & RP).

The Model seems to have fixed alot of the prudish issues of the last model.

The new Exprimental merge method Della builds upon DARE, It uses adaptive pruning based on parameter magnitudes. DELLA first ranks parameters in each row of delta parameters and assigns drop probabilities inversely proportional to their magnitudes. This allows it to retain more important changes while reducing interference. After pruning, it rescales the remaining parameters similar to DARE.

Quants:

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

SteelQuants, My Personal Quants

G2-DA-Nyxora-27b-V2-Q5_K_M-GGUF

G2-DA-Nyxora-27b-V2-Q4_K_M-GGUF

Config:

MODEL_NAME = "G2-DA-Nyxora-27b-V2"
yaml_config = """
base_model: TheDrummer/Big-Tiger-Gemma-27B-v1
merge_method: della
dtype: bfloat16
models:
  - model: TheDrummer/Gemmasutra-Pro-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>

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

Downloads last month: 13

Model tree for SteelStorage/G2-DA-Nyxora-27b-V2

TheDrummer/Big-Tiger-Gemma-27B-v1

TheDrummer/Gemmasutra-Pro-27B-v1

migtissera/Tess-v2.5-Gemma-2-27B-alpha

Merge model

this model

Merges

2 models

Quantizations

5 models