Instructions to use Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2 with Transformers:

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

pipe = pipeline("text-generation", model="Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2")
model = AutoModelForMultimodalLM.from_pretrained("Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2")
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 Settings

vLLM

How to use Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2

SGLang

How to use Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2 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 "Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2" \
    --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": "Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2",
		"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 "Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2" \
        --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": "Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2 with Docker Model Runner:
```
docker model run hf.co/Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-7.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using unsloth/Mistral-Small-Instruct-2409 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: anthracite-org/magnum-v4-22b
    parameters:
      weight: 1.0         # Primary model for human-like writing
      density: 0.88       # Solid foundation for clear, balanced text generation
  - model: TheDrummer/Cydonia-22B-v1.3
    parameters:
      weight: 0.26        # Slightly reduced weight for nuanced creativity
      density: 0.7        # Maintains subtle creative influence
  - model: TheDrummer/Cydonia-22B-v1.2
    parameters:
      weight: 0.16        # Adjusted for balanced creativity without interference
      density: 0.68       # Harmonized with other storytelling contributions
  - model: TheDrummer/Cydonia-22B-v1.1
    parameters:
      weight: 0.18        # Refined for precision in roleplay and nuanced content
      density: 0.68       # Ensures stability without overwhelming integration
  - model: Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
    parameters:
      weight: 0.28        # Balanced for storytelling depth without dominance
      density: 0.77       # Smooth integration for narrative-driven content
  - model: allura-org/MS-Meadowlark-22B
    parameters:
      weight: 0.3         # Retains balanced creativity and descriptive clarity
      density: 0.72       # Enhances fluency and narrative cohesion
  - model: spow12/ChatWaifu_v2.0_22B
    parameters:
      weight: 0.27        # Maintains anime-style RP and conversational tone
      density: 0.7        # Preserved for compatibility with other models
  - model: Saxo/Linkbricks-Horizon-AI-Japanese-Superb-V1-22B
    parameters:
      weight: 0.2         # Specialized for Japanese linguistic contexts
      density: 0.58       # Fine-tuned for focused coherence
  - model: crestf411/MS-sunfall-v0.7.0
    parameters:
      weight: 0.25        # Subtle tone for dramatic storytelling
      density: 0.74       # Balanced for integration with other narrative styles
  - model: unsloth/Mistral-Small-Instruct-2409+rAIfle/Acolyte-LORA
    parameters:
      weight: 0.24        # Subtle addition for structured content variation
      density: 0.7        # Aligns seamlessly with the overall blend
  - model: InferenceIllusionist/SorcererLM-22B
    parameters:
      weight: 0.23        # Provides stylistic coherence
      density: 0.74       # Supports expressive and balanced outputs
  - model: unsloth/Mistral-Small-Instruct-2409+Kaoeiri/Moingooistrial-22B-V1-Lora
    parameters:
      weight: 0.26        # Mythical and monster storytelling
      density: 0.72       # Balanced for integration with core models
  - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
    parameters:
      weight: 0.12        # Light roleplay influence to prevent overheating
      density: 0.65       # Keeps roleplay-heavy elements in check
  - model: byroneverson/Mistral-Small-Instruct-2409-abliterated
    parameters:
      weight: 0.15        # Provides raw and unfiltered context
      density: 0.68       # Harmonizes with primary base model

merge_method: dare_ties  # Optimal for diverse and complex model blending
base_model: unsloth/Mistral-Small-Instruct-2409
parameters:
  density: 0.85          # Overall density ensures logical and creative balance
  epsilon: 0.09          # Small step size for smooth blending
  lambda: 1.22           # Adjusted scaling for refined sharpness and coherence
dtype: bfloat16