Text Generation
Transformers
Safetensors
French
gpt2
SLM
Neko-SLM
Nekolien
Créativité
Nelya
conlangs
conversational
text-generation-inference
Instructions to use Finisha-F-scratch/Nelya with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Finisha-F-scratch/Nelya with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Finisha-F-scratch/Nelya") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Finisha-F-scratch/Nelya") model = AutoModelForCausalLM.from_pretrained("Finisha-F-scratch/Nelya", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Finisha-F-scratch/Nelya with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Finisha-F-scratch/Nelya" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Finisha-F-scratch/Nelya", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Finisha-F-scratch/Nelya
- SGLang
How to use Finisha-F-scratch/Nelya 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 "Finisha-F-scratch/Nelya" \ --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": "Finisha-F-scratch/Nelya", "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 "Finisha-F-scratch/Nelya" \ --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": "Finisha-F-scratch/Nelya", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Finisha-F-scratch/Nelya with Docker Model Runner:
docker model run hf.co/Finisha-F-scratch/Nelya
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,3 +15,32 @@ tags:
|
|
| 15 |
- Nelya
|
| 16 |
library_name: transformers
|
| 17 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
- Nelya
|
| 16 |
library_name: transformers
|
| 17 |
---
|
| 18 |
+
|
| 19 |
+
# 🌸 Nelya - mini-Assistante Nekolienne
|
| 20 |
+
|
| 21 |
+

|
| 22 |
+
|
| 23 |
+
Nelya est un **SLM** (small language model),
|
| 24 |
+
Crée from scratch (de zéro) à partir de notre modèle de fondation : **Lam-4-zero-F**.
|
| 25 |
+
|
| 26 |
+
Nelya excelle a générer des phrases en nekolien. Le nekolien est une langue artificielle, que nous avons imaginée et conçu nous même.
|
| 27 |
+
Nous l'avons créées originairement pour nos chansons et notre créativité,
|
| 28 |
+
Mais nous nous sommes dit qu'une IA qui parle notre langue n'était pas une mauvaise idée.
|
| 29 |
+
|
| 30 |
+
# ✨ Cas d'usage 🌸
|
| 31 |
+
|
| 32 |
+
* - Créativité
|
| 33 |
+
* - exploration de la langue
|
| 34 |
+
|
| 35 |
+
Vous pouvez générer du texte avec Nelya,
|
| 36 |
+
Pour explorer la créativité de notre propre langue.
|
| 37 |
+
Nelya prouve que les modèles de languages ne sont pas seulement des assistants généralistes qui parlent qu'anglais ou français,
|
| 38 |
+
Ils peuvent parler le langage que vous souhaitez.
|
| 39 |
+
|
| 40 |
+
# ♥️ License de Nelya 🩷
|
| 41 |
+
|
| 42 |
+
Attention, l'utilisation de Nelya est régi par la licence Nelya-restrictive,
|
| 43 |
+
qui n'est pas open source.
|
| 44 |
+
Notre licence interdit tout affinage ou utilisation commerciale de Nelya.
|
| 45 |
+
|
| 46 |
+
**✨ Amusée vous bien a utiliser Nelya ✨**
|