Instructions to use exau/agritgllm-modeles with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use exau/agritgllm-modeles with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf exau/agritgllm-modeles:Q4_K_M # Run inference directly in the terminal: llama cli -hf exau/agritgllm-modeles:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf exau/agritgllm-modeles:Q4_K_M # Run inference directly in the terminal: llama cli -hf exau/agritgllm-modeles:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf exau/agritgllm-modeles:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf exau/agritgllm-modeles:Q4_K_M
Use Docker
docker model run hf.co/exau/agritgllm-modeles:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use exau/agritgllm-modeles with Ollama:
ollama run hf.co/exau/agritgllm-modeles:Q4_K_M
- Unsloth Desktop
- Pi
How to use exau/agritgllm-modeles with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf exau/agritgllm-modeles:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "exau/agritgllm-modeles:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use exau/agritgllm-modeles with Docker Model Runner:
docker model run hf.co/exau/agritgllm-modeles:Q4_K_M
- Lemonade
How to use exau/agritgllm-modeles with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull exau/agritgllm-modeles:Q4_K_M
Run and chat with the model
lemonade run user.agritgllm-modeles-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use exau/agritgllm-modeles with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf exau/agritgllm-modeles:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default exau/agritgllm-modeles:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use exau/agritgllm-modeles with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf exau/agritgllm-modeles:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "exau/agritgllm-modeles:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Modèles de l'application AgriTGLLM
Copies, sans aucune modification, des modèles qu'utilise l'application AgriTGLLM (registre agricole hors ligne). L'application les télécharge ici une seule fois, vérifie leur taille et leur empreinte SHA-256, puis fonctionne sans internet.
| Fichier | Rôle | Taille (octets) | SHA-256 | Origine | Licence |
|---|---|---|---|---|---|
LFM2.5-350M-Q4_K_M.gguf |
compréhension des phrases (modèle principal depuis le 18/11/2026) | 229 312 224 | 7e6f72643caafc9a68256686638c4d7916f2cec76d1df478d4c3ddcd95a6aed4 |
LiquidAI/LFM2.5-350M-GGUF (révision 657e078c94084481950a2d555a941481f715536b) |
LFM Open License v1.0 (LICENSE-LFM2.5-350M.txt) |
ggml-large-v3-turbo-q5_0.bin |
dictée (transcription en français) | 574 041 195 | 394221709cd5ad1f40c46e6031ca61bce88931e6e088c188294c6d5a55ffa7e2 |
openai/whisper-large-v3-turbo, conversion ggerganov/whisper.cpp (révision 5359861c739e955e79d9a303bcbc70fb988958b1) |
MIT (LICENSE-Whisper.txt) |
LFM Open License v1.0 : licence de type Apache 2.0 avec une limite d'usage commercial (article 5). L'usage commercial n'est couvert que pour une entité (groupe compris) dont le chiffre d'affaires annuel est inférieur à 10 millions de dollars US. Au-delà, une licence commerciale de Liquid AI est nécessaire.
Ces fichiers ne contiennent aucune donnée d'exploitation : aucun fine-tuning n'a été appliqué. Tous les droits sur les modèles restent à leurs auteurs.
- Downloads last month
- 35
4-bit