Instructions to use AuriAetherwiing/MN-12B-Starcannon-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AuriAetherwiing/MN-12B-Starcannon-v2 with Transformers:

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

pipe = pipeline("text-generation", model="AuriAetherwiing/MN-12B-Starcannon-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AuriAetherwiing/MN-12B-Starcannon-v2")
model = AutoModelForCausalLM.from_pretrained("AuriAetherwiing/MN-12B-Starcannon-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AuriAetherwiing/MN-12B-Starcannon-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AuriAetherwiing/MN-12B-Starcannon-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": "AuriAetherwiing/MN-12B-Starcannon-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AuriAetherwiing/MN-12B-Starcannon-v2

SGLang

How to use AuriAetherwiing/MN-12B-Starcannon-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 "AuriAetherwiing/MN-12B-Starcannon-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": "AuriAetherwiing/MN-12B-Starcannon-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 "AuriAetherwiing/MN-12B-Starcannon-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": "AuriAetherwiing/MN-12B-Starcannon-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AuriAetherwiing/MN-12B-Starcannon-v2 with Docker Model Runner:
```
docker model run hf.co/AuriAetherwiing/MN-12B-Starcannon-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

UPD: this model series is succeeded by EVA
Unprivated, to store for historical reasons
There's not much point in those merges, Celeste 70B 0.1 pretty much melded Celeste's and Magnum's datasets anyway
To be continued, but on a different base, under a different name, and actually trained this time, without shortcuts

MN-12B-Starcannon-v2

This is a merge of pre-trained language models created using mergekit. Turned out to be a bit more Magnum-esque, but still is very creative, and writing style is pretty nice, even if some slop words appear time to time. Might be a good fit for people wanting more variety than Magnum has, and more verbose prose than Celeste v1.9 has.

Dynamic FP8
Static GGUF (by Mradermacher)
EXL2 (by kingbri of RoyalLab)

Merge Details

Merge Method

This model was merged using the TIES merge method using nothingiisreal/MN-12B-Celeste-V1.9 as a base.

Merge fodder

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
    - model: intervitens/mini-magnum-12b-v1.1
      parameters:
        density: 0.3
        weight: 0.5
    - model: nothingiisreal/MN-12B-Celeste-V1.9
      parameters:
        density: 0.7
        weight: 0.5

merge_method: ties
base_model: nothingiisreal/MN-12B-Celeste-V1.9
parameters:
    normalize: true
    int8_mask: true
dtype: bfloat16