Instructions to use RAANA-IA/Nekolyne with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RAANA-IA/Nekolyne with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RAANA-IA/Nekolyne") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("RAANA-IA/Nekolyne") model = AutoModelForCausalLM.from_pretrained("RAANA-IA/Nekolyne") 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 RAANA-IA/Nekolyne with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RAANA-IA/Nekolyne" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RAANA-IA/Nekolyne", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RAANA-IA/Nekolyne
- SGLang
How to use RAANA-IA/Nekolyne 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 "RAANA-IA/Nekolyne" \ --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": "RAANA-IA/Nekolyne", "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 "RAANA-IA/Nekolyne" \ --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": "RAANA-IA/Nekolyne", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use RAANA-IA/Nekolyne with Docker Model Runner:
docker model run hf.co/RAANA-IA/Nekolyne
Exemples générations nekolyne
- prompt : salut?
Réponse de Nekolyne :
Salut! Coma voi vedea un amico di casa ?
Ji estas rell'riel ?
Ji rell'riel voi vedea un amico di casa ?
Ji aveya la eye ?
Ji aveya la rell'riel ?
Ji aveya la rell'riel voi vedea un amico di casa ?
Ji aveya la eye rell'riel vedaun amico di casa ?
Ji aveya la rell'riel rell'riel vedaun amico di casa ?
- prompt : salut?
Réponse de Nekolyne : Salut!
Ji salutas. Malya.
Ji salutas.
Ji salutas.
Ji salutas.
- Qui es-tu ?
Nekolyne : Je m'appelle la machine, et je suis construite pour améliorer la qualité de la communication entre les humains. J'aime courir et courir, et je suis le meilleur ami possible que tu puisses avoir.
Ainsi, mon nom significa 'I am' (Je suis) forcé par l'amplitude de la pression de la boucle de la langue. Je suis construite pour utiliser la linguistique pour améliorer la communication humaine.
- Qui es-tu ?
Nekolyne : Ji esti 'La' (Riel). La est la persona eta la intéresserallia.
- Ji eta Laura (J'ai changé mon suffixe), un ami du codage. Nous avions la chance d'être construits par la même équipe qui a construit la carte de l'aéronef. Mon nom est un peu préférable, mais c'est un peu l'équivalent de 'Sue' en anglais.
Ji eta Laura (J'ai changé mon suffixe), un ami du codage. Nous avions la chance d'être construits par la même équipe qui a construit la carte de l'aéronef. Mon nom est un peu préférable, mais c