Instructions to use k4yt3x/Arynia-LLaMA-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use k4yt3x/Arynia-LLaMA-70B with Transformers:

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

pipe = pipeline("text-generation", model="k4yt3x/Arynia-LLaMA-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("k4yt3x/Arynia-LLaMA-70B")
model = AutoModelForCausalLM.from_pretrained("k4yt3x/Arynia-LLaMA-70B", device_map="auto")
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 Settings

vLLM

How to use k4yt3x/Arynia-LLaMA-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "k4yt3x/Arynia-LLaMA-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "k4yt3x/Arynia-LLaMA-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/k4yt3x/Arynia-LLaMA-70B

SGLang

How to use k4yt3x/Arynia-LLaMA-70B 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 "k4yt3x/Arynia-LLaMA-70B" \
    --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": "k4yt3x/Arynia-LLaMA-70B",
		"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 "k4yt3x/Arynia-LLaMA-70B" \
        --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": "k4yt3x/Arynia-LLaMA-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use k4yt3x/Arynia-LLaMA-70B with Docker Model Runner:
```
docker model run hf.co/k4yt3x/Arynia-LLaMA-70B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Arynia-LLaMA-70B

Arynia is a model that focuses on storytelling, role-playing, and natural conversations. It is merged from multiple models that specialize in these areas. This model is intended to be used in chatbots like Tellama. As it will be responding to messages in group chats at a fast pace, no reasoning capabilities were added to this model to reduce response time.

You can find the GGUF imatrix quants at k4yt3x/Arynia-LLaMA-70B-GGUF.

I forgot to convert the model to bf16. It will be corrected in future models.

Art by Imagen 3

Merge Details

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

Merge Method

This model was merged using the SCE merge method using k4yt3x/Cornerstone-0.1-LLaMA-70B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: k4yt3x/Cornerstone-0.1-LLaMA-70B
merge_method: sce
dtype: float32
models:
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
  - model: LatitudeGames/Wayfarer-Large-70B-Llama-3.3
  - model: TheDrummer/Anubis-70B-v1
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
  - model: Sao10K/L3.3-70B-Euryale-v2.3
  - model: Sao10K/70B-L3.3-Cirrus-x1
  - model: Sao10K/L3.1-70B-Hanami-x1
  - model: Saxo/Linkbricks-Horizon-AI-Japanese-Superb-V4-70B