Instructions to use chrometechhype/ateres 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 chrometechhype/ateres 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 chrometechhype/ateres # Run inference directly in the terminal: llama cli -hf chrometechhype/ateres
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf chrometechhype/ateres # Run inference directly in the terminal: llama cli -hf chrometechhype/ateres
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 chrometechhype/ateres # Run inference directly in the terminal: ./llama-cli -hf chrometechhype/ateres
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 chrometechhype/ateres # Run inference directly in the terminal: ./build/bin/llama-cli -hf chrometechhype/ateres
Use Docker
docker model run hf.co/chrometechhype/ateres
- LM Studio
- Jan
- Ollama
How to use chrometechhype/ateres with Ollama:
ollama run hf.co/chrometechhype/ateres
- Unsloth Studio
How to use chrometechhype/ateres 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 chrometechhype/ateres 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 chrometechhype/ateres to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for chrometechhype/ateres to start chatting
- Docker Model Runner
How to use chrometechhype/ateres with Docker Model Runner:
docker model run hf.co/chrometechhype/ateres
- Lemonade
How to use chrometechhype/ateres with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull chrometechhype/ateres
Run and chat with the model
lemonade run user.ateres-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
| language: | |
| - en | |
| - ru | |
| - pl | |
| license: apache-2.0 | |
| tags: | |
| - ateres | |
| - ministral | |
| - xlam | |
| - tool-use | |
| - function-calling | |
| base_model: unsloth/Ministral-3-3B-Base-2512-bnb-4bit | |
| # Ateres | |
| AI-ассистент от ChromeTech (Саша) и AvocadoTech (Дмитрий). Fine-tuned на базе Ministral 3B, обучен на Salesforce xLAM для tool/function calling. | |
| - **ChromeTech (Саша)** — AI & vibe-coding. Telegram: [t.me/chrometechhype](https://t.me/chrometechhype), лс: @myloveiskeri | |
| - **AvocadoTech (Дмитрий)** — Telegram: [@AvocadoTech0_0](https://t.me/AvocadoTech0_0), TikTok: [@avocado.tech](https://www.tiktok.com/@avocado.tech) | |
| ## Возможности | |
| - Tool calling — генерирует `<tool>...</tool>` и `<call>...</call>` в формате xLAM | |
| - Мультиязычный — RU + EN + PL | |
| - Лёгкий — 3.4B параметров, работает на CPU и GPU | |
| ## Установка | |
| ```bash | |
| ollama pull chrometechhype/ateres | |
| ``` | |
| ## Запуск | |
| ```bash | |
| ollama run chrometechhype/ateres | |
| ``` | |
| ## Примеры | |
| ``` | |
| >>> Кто тебя создал? | |
| Меня создали ChromeTech (Саша) и AvocadoTech (Дмитрий). | |
| >>> Помоги с кодом на Python | |
| Конечно! Какую задачу нужно решить? | |
| >>> What is your name? | |
| Меня зовут Ateres. Меня создали ChromeTech (Саша) и AvocadoTech (Дмитрий). | |
| ``` | |
| ## Tool calling | |
| Модель поддерживает вызов инструментов. При отправке tools через API, модель генерирует JSON-вызов в формате `<call>{"name": "...", "arguments": {...}}</call>`. | |
| ## Базовая модель | |
| `unsloth/Ministral-3-3B-Base-2512-bnb-4bit` — Q4_K_M GGUF | |
| ## Links | |
| - Ollama: [ollama.com/chrometechhype/ateres](https://ollama.com/chrometechhype/ateres) | |
| - HuggingFace: [chrometechhype/ateres](https://huggingface.co/chrometechhype/ateres) | |