Instructions to use evalexik/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 evalexik/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 evalexik/modeles:Q4_K_M # Run inference directly in the terminal: llama cli -hf evalexik/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 evalexik/modeles:Q4_K_M # Run inference directly in the terminal: llama cli -hf evalexik/modeles:Q4_K_M
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 evalexik/modeles:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf evalexik/modeles:Q4_K_M
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 evalexik/modeles:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf evalexik/modeles:Q4_K_M
Use Docker
docker model run hf.co/evalexik/modeles:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use evalexik/modeles with Ollama:
ollama run hf.co/evalexik/modeles:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use evalexik/modeles with Docker Model Runner:
docker model run hf.co/evalexik/modeles:Q4_K_M
- Lemonade
How to use evalexik/modeles with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull evalexik/modeles:Q4_K_M
Run and chat with the model
lemonade run user.modeles-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Modèles d'Evalexik
Ce dépôt contient les modèles que le logiciel Evalexik (Evalexik Inc., https://evalexik.com)
télécharge après son installation. Ce sont des copies figées de modèles publiés par leurs auteurs
sous licence libre : Evalexik vérifie l'empreinte SHA-256 de chaque fichier (voir manifest.json)
avant de s'en servir.
This repository holds frozen copies of openly licensed models downloaded by the Evalexik software.
Each file is checked against the SHA-256 fingerprint listed in manifest.json.
| Fichier | Rôle dans Evalexik | Origine | Licence |
|---|---|---|---|
AIModels/Mistral-7B-Instruct-v0.3-Q4_K_M.gguf |
Rédaction locale | Mistral AI, Mistral-7B-Instruct-v0.3 ; quantification GGUF Q4_K_M identique à celle de lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF |
Apache 2.0 (LICENSES/Apache-2.0.txt) |
SpeechModels/whisper/ggml-large-v3-turbo.bin |
Transcription | OpenAI, Whisper large-v3-turbo ; format ggml identique à celui de ggerganov/whisper.cpp |
MIT (LICENSES/MIT-Whisper-OpenAI.txt, LICENSES/MIT-whisper.cpp-ggml.txt) |
SpeechModels/fr/vosk/… |
Dictée en français | Alpha Cephei, vosk-model-fr-0.22, sans les dossiers rescore et rnnlm |
Apache 2.0 (LICENSES/Apache-2.0.txt) |
SpeechModels/fr/phonemes.onnx, SpeechModels/fr/phonemes.json |
Analyse phonétique | Bofeng Huang, phonemizer-wav2vec2-ctc-french, exporté en ONNX par Evalexik Inc. | MIT (LICENSES/MIT-phonemizer-wav2vec2-ctc-french.txt) |
Les fichiers sont redistribués sans modification de leurs poids, sauf l'export ONNX du modèle phonétique et l'allègement du modèle Vosk décrits ci-dessus.
- Downloads last month
- -
4-bit