Instructions to use mergekit-community/MN-Hekate-Nykhia-17B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mergekit-community/MN-Hekate-Nykhia-17B with Transformers:

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

pipe = pipeline("text-generation", model="mergekit-community/MN-Hekate-Nykhia-17B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mergekit-community/MN-Hekate-Nykhia-17B")
model = AutoModelForCausalLM.from_pretrained("mergekit-community/MN-Hekate-Nykhia-17B")
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 mergekit-community/MN-Hekate-Nykhia-17B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mergekit-community/MN-Hekate-Nykhia-17B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mergekit-community/MN-Hekate-Nykhia-17B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mergekit-community/MN-Hekate-Nykhia-17B

SGLang

How to use mergekit-community/MN-Hekate-Nykhia-17B 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 "mergekit-community/MN-Hekate-Nykhia-17B" \
    --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": "mergekit-community/MN-Hekate-Nykhia-17B",
		"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 "mergekit-community/MN-Hekate-Nykhia-17B" \
        --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": "mergekit-community/MN-Hekate-Nykhia-17B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mergekit-community/MN-Hekate-Nykhia-17B with Docker Model Runner:
```
docker model run hf.co/mergekit-community/MN-Hekate-Nykhia-17B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using mergekit-community/MN-Hekate-Geneteira-17B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mergekit-community/MN-Hekate-Geneteira-17B
slices:
  - sources:
    - model: mergekit-community/MN-Hekate-Geneteira-17B
      layer_range: [0, 20]

  - sources:
    - model: mergekit-community/MN-Hekate-Geneteira-17B
      layer_range: [20, 36]
      parameters:
        weight: [0.4, 0.2]
    - model: mistralai/Mistral-Nemo-Base-2407
      layer_range: [16, 32]
      parameters:
        weight: [2, 1.5]
    - model: PygmalionAI/Eleusis-12B
      layer_range: [16, 32]
    - model: LatitudeGames/Wayfarer-12B
      layer_range: [16, 32]
      parameters:
        weight: [1.5, 1.49, 1.46, 1.4, 1.33, 1.25, 1.15, 1.05, 1]
    - model: PocketDoc/Dans-DangerousWinds-V1.1.0-12b
      layer_range: [16, 32]
      parameters:
        weight: [1.5, 1.49, 1.46, 1.4, 1.33, 1.25, 1.15, 1.05, 1]
    - model: elinas/Chronos-Gold-12B-1.0
      layer_range: [16, 32]
      parameters:
        weight: [1.0, 1.1, 1.2, 1.29, 1.37, 1.43, 1.48, 1.5, 1.5]
    - model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
      layer_range: [16, 32]
      parameters:
        weight: [1.0, 1.1, 1.2, 1.29, 1.37, 1.43, 1.48, 1.5, 1.5]

  - sources:
    - model: mergekit-community/MN-Hekate-Geneteira-17B
      layer_range: [36, 56]

tokenizer:
  source: union
  tokens:
    "[INST]":
      source: mergekit-community/MN-Hekate-Geneteira-17B
      force: true
    "[/INST]":
      source: mergekit-community/MN-Hekate-Geneteira-17B
      force: true
    "<|im_start|>":
      source: mergekit-community/MN-Hekate-Geneteira-17B
      force: true
    "<|im_end|>":
      source: mergekit-community/MN-Hekate-Geneteira-17B
      force: true