Instructions to use Dorian2B/Vera-Instruct-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dorian2B/Vera-Instruct-Q8_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Dorian2B/Vera-Instruct-Q8_0-GGUF",
	filename="vera-instruct-q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Dorian2B/Vera-Instruct-Q8_0-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use Dorian2B/Vera-Instruct-Q8_0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dorian2B/Vera-Instruct-Q8_0-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dorian2B/Vera-Instruct-Q8_0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0

Ollama
How to use Dorian2B/Vera-Instruct-Q8_0-GGUF with Ollama:
```
ollama run hf.co/Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0
```

Unsloth Studio new

How to use Dorian2B/Vera-Instruct-Q8_0-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Dorian2B/Vera-Instruct-Q8_0-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Dorian2B/Vera-Instruct-Q8_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Dorian2B/Vera-Instruct-Q8_0-GGUF to start chatting

Docker Model Runner
How to use Dorian2B/Vera-Instruct-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0
```

Lemonade

How to use Dorian2B/Vera-Instruct-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Dorian2B/Vera-Instruct-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.Vera-Instruct-Q8_0-GGUF-Q8_0

List all available models

lemonade list

Vera - Instruct

Description :

Vera est une intelligence artificielle légère et performante, spécialisée dans les interactions en français. Optimisée pour fonctionner en local, elle offre des réponses rapides et pertinentes, même sur des configurations matérielles modestes.

Caractéristiques clés :

Modèle léger (2.6B de paramètres) : Idéal pour une utilisation locale, y compris sur mobile
Spécialisation en français : Compréhension et génération de texte de haute qualité
Formats disponibles : GGUF (Llama.cpp/Ollama) et PyTorch
Open Source : License Apache 2.0

Téléchargement et utilisation :

Option 1 : Via Ollama

ollama run hf.co/Dorian2B/Vera-Instruct-Q8_0-GGUF

Option 2 : Téléchargement direct (GGUF)

Modèle GGUF Quantifié (Q8_0)

Option 3 : Utilisation avec Python (PyTorch)

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Dorian2B/Vera-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

input_text = "Bonjour Vera, comment ça va ?"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Cas d'usage :

Assistance personnelle hors ligne
Réponses rapides en français
Solutions pour appareils à ressources limitées

Notes :

Fonctionnement 100% local respectant la vie privée
Performances optimales sur CPU/GPU (format GGUF)
Poids du modèle : ~2.8GB (Q8_0)

Downloads last month: 8

GGUF

Model size

3B params

Architecture

gemma2

Hardware compatibility

8-bit

Model tree for Dorian2B/Vera-Instruct-Q8_0-GGUF

Base model

Dorian2B/Vera-Instruct

Quantized

(3)

this model