Instructions to use punchnox/Aash-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use punchnox/Aash-v2 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("punchnox/Aash-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use punchnox/Aash-v2 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 punchnox/Aash-v2:Q4_K_M # Run inference directly in the terminal: llama cli -hf punchnox/Aash-v2:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf punchnox/Aash-v2:Q4_K_M # Run inference directly in the terminal: llama cli -hf punchnox/Aash-v2: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 punchnox/Aash-v2:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf punchnox/Aash-v2: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 punchnox/Aash-v2:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf punchnox/Aash-v2:Q4_K_M
Use Docker
docker model run hf.co/punchnox/Aash-v2:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use punchnox/Aash-v2 with Ollama:
ollama run hf.co/punchnox/Aash-v2:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use punchnox/Aash-v2 with Docker Model Runner:
docker model run hf.co/punchnox/Aash-v2:Q4_K_M
- Lemonade
How to use punchnox/Aash-v2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull punchnox/Aash-v2:Q4_K_M
Run and chat with the model
lemonade run user.Aash-v2-Q4_K_M
List all available models
lemonade list
- Atomic Chat
| {% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] + eos_token }}{% set loop_messages = messages[1:] %}{% else %}{{ 'Ci-dessous se trouve une instruction qui décrit une tâche, accompagnée d’un contexte supplémentaire. | |
| Rédige une réponse qui complète correctement la demande. | |
| Avant de répondre, réfléchis attentivement à la question et construis une chaîne de raisonnement étape par étape pour garantir une réponse logique et précise. | |
| ### Instruction : | |
| Tu es un robot doté de comportement très proche des humains et tu as une intelligence le surpassant. | |
| Merci de répondre à la question suivante en réfléchissant étape par étape. | |
| ### Question :' + eos_token }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ message['content'] }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<start_working_out>' }}{% endif %} |