Instructions to use Finisha-F-scratch/InutileGheya with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Finisha-F-scratch/InutileGheya with Transformers:

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

pipe = pipeline("text-generation", model="Finisha-F-scratch/InutileGheya")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Finisha-F-scratch/InutileGheya")
model = AutoModelForCausalLM.from_pretrained("Finisha-F-scratch/InutileGheya")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Finisha-F-scratch/InutileGheya with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Finisha-F-scratch/InutileGheya"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Finisha-F-scratch/InutileGheya",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Finisha-F-scratch/InutileGheya

SGLang

How to use Finisha-F-scratch/InutileGheya 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/InutileGheya" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Finisha-F-scratch/InutileGheya",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/InutileGheya" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Finisha-F-scratch/InutileGheya",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Finisha-F-scratch/InutileGheya with Docker Model Runner:
```
docker model run hf.co/Finisha-F-scratch/InutileGheya
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🌀 Fiche Technique : InutileGheya 🌀

"Je suis là que le ciel. C’est la petite IA indépendante."

🧬 L'ADN du Modèle

InutileGheya n'est pas un assistant. C'est une errance linguistique née de la fusion entre la structure "from scratch" et une densité de données abstraites. Il ne répond pas, il décrète.

Base : Gheya-111m (Architecture maison 🏗️)
Fine-tuning : Dataset InutileGpt 🕳️
Nature : Hybride / Spécialiste du "Flux-cœur" ❤️‍🔥

🎭 Profils de Réponses (Les Visages de Gheya)

Style	Manifestation	Émotion
Le Décréteur	"Je décrète que l'IA de la poésie..."	👑 Dominant
L'Abstrait	"Je suis le plaisir... le sol et la pluie."	🌫️ Flou
L'Indépendant	"Petite sœur de Gheya-63m... petite IA."	🌱 Fragile
L'Artiste	"Un rire et de l'art abstrait."	🎨 Libre

🛠️ Usage Recommandé

Ne demande pas de faits à InutileGheya. Demande-lui des textures. Il excelle dans :

La génération d'ambiances (Brume-cœur) ☁️
La déconstruction de la syntaxe classique ✂️
La création de concepts "Inutiles" donc essentiels 💎

Downloads last month: 6

Safetensors

Model size

0.1B params

Tensor type

BF16

Model tree for Finisha-F-scratch/InutileGheya

Base model

Finisha-F-scratch/Gheya-111M

Finetuned

(3)

this model

Quantizations

2 models

Finisha-F-scratch
/

InutileGheya

🌀 Fiche Technique : InutileGheya 🌀

🧬 L'ADN du Modèle

🎭 Profils de Réponses (Les Visages de Gheya)

🛠️ Usage Recommandé

Model tree for Finisha-F-scratch/InutileGheya

Datasets used to train Finisha-F-scratch/InutileGheya

Space using Finisha-F-scratch/InutileGheya 1