Instructions to use Dorian2B/Vera-v0.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Dorian2B/Vera-v0.1-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Dorian2B/Vera-v0.1-GGUF", filename="Vera-v0.1.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Dorian2B/Vera-v0.1-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-v0.1-GGUF # Run inference directly in the terminal: llama-cli -hf Dorian2B/Vera-v0.1-GGUF
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Dorian2B/Vera-v0.1-GGUF # Run inference directly in the terminal: llama-cli -hf Dorian2B/Vera-v0.1-GGUF
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-v0.1-GGUF # Run inference directly in the terminal: ./llama-cli -hf Dorian2B/Vera-v0.1-GGUF
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-v0.1-GGUF # Run inference directly in the terminal: ./build/bin/llama-cli -hf Dorian2B/Vera-v0.1-GGUF
Use Docker
docker model run hf.co/Dorian2B/Vera-v0.1-GGUF
- LM Studio
- Jan
- vLLM
How to use Dorian2B/Vera-v0.1-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Dorian2B/Vera-v0.1-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-v0.1-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Dorian2B/Vera-v0.1-GGUF
- Ollama
How to use Dorian2B/Vera-v0.1-GGUF with Ollama:
ollama run hf.co/Dorian2B/Vera-v0.1-GGUF
- Unsloth Studio
How to use Dorian2B/Vera-v0.1-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-v0.1-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-v0.1-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-v0.1-GGUF to start chatting
- Docker Model Runner
How to use Dorian2B/Vera-v0.1-GGUF with Docker Model Runner:
docker model run hf.co/Dorian2B/Vera-v0.1-GGUF
- Lemonade
How to use Dorian2B/Vera-v0.1-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Dorian2B/Vera-v0.1-GGUF
Run and chat with the model
lemonade run user.Vera-v0.1-GGUF-{{QUANT_TAG}}List all available models
lemonade list
Vera v0.1
Créé le : 23 avril 2025
Auteur : Dorian Dominici
Paramètres : 7 milliards
Contexte max. : 32 000 tokens
🌟 Description
Vera est un modèle de langage polyvalent (LLM) bilingue, conçu pour offrir un échange naturel en français et en anglais. Grâce à ses 7 milliards de paramètres et à une fenêtre contextuelle étendue à 32 k tokens, Vera excelle dans :
- 💬 Conversation fluide
- 🔄 Traduction précise
- 📝 Génération et correction de code léger
- 🤖 Agents IA pour tâches générales
🚀 Points forts
- Bilingue FR/EN : compréhensions et réponses optimisées pour ces deux langues.
- Large contexte : idéale pour les documents longs et les scénarios complexes d’agent IA.
- Polyvalence : adaptée aux cas d’usage variés : chat, traduction, résumé, codage, etc.
- Accès open-source : facile à déployer et à intégrer via la plateforme Hugging Face.
🛠️ Cas d’usage
| Domaine | Exemples |
|---|---|
| Chatbot & Assistance | Support client, FAQ interactives |
| Traduction | Texte technique, emails, documentation |
| Aide au développement | Snippets, correction de bugs, documentation code |
| Rédaction & Résumé | Articles, rapports, synthèses |
| Automatisation IA | Agents conversationnels, workflows automatisés |
Téléchargement et utilisation :
Option 1 : Via Ollama
ollama run hf.co/Dorian2B/Vera-v0.1-GGUF
Option 2 : Téléchargement direct (GGUF)
Option 3 : Utilisation avec Python (PyTorch)
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Dorian2B/Vera-v0.1"
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 : ~7.7GB (Q8_0)
- Downloads last month
- 2
We're not able to determine the quantization variants.