Instructions to use ChessVania/salgrai-alpha-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChessVania/salgrai-alpha-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ChessVania/salgrai-alpha-v1",
	filename="salgrai-test-v1-f32.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 ChessVania/salgrai-alpha-v1 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 ChessVania/salgrai-alpha-v1:F32
# Run inference directly in the terminal:
llama cli -hf ChessVania/salgrai-alpha-v1:F32

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ChessVania/salgrai-alpha-v1:F32
# Run inference directly in the terminal:
llama cli -hf ChessVania/salgrai-alpha-v1:F32

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 ChessVania/salgrai-alpha-v1:F32
# Run inference directly in the terminal:
./llama-cli -hf ChessVania/salgrai-alpha-v1:F32

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 ChessVania/salgrai-alpha-v1:F32
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ChessVania/salgrai-alpha-v1:F32

Use Docker

docker model run hf.co/ChessVania/salgrai-alpha-v1:F32

LM Studio
Jan

vLLM

How to use ChessVania/salgrai-alpha-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChessVania/salgrai-alpha-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChessVania/salgrai-alpha-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ChessVania/salgrai-alpha-v1:F32

Ollama
How to use ChessVania/salgrai-alpha-v1 with Ollama:
```
ollama run hf.co/ChessVania/salgrai-alpha-v1:F32
```

Unsloth Studio

How to use ChessVania/salgrai-alpha-v1 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 ChessVania/salgrai-alpha-v1 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 ChessVania/salgrai-alpha-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ChessVania/salgrai-alpha-v1 to start chatting

Atomic Chat new
Docker Model Runner
How to use ChessVania/salgrai-alpha-v1 with Docker Model Runner:
```
docker model run hf.co/ChessVania/salgrai-alpha-v1:F32
```

Lemonade

How to use ChessVania/salgrai-alpha-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ChessVania/salgrai-alpha-v1:F32

Run and chat with the model

lemonade run user.salgrai-alpha-v1-F32

List all available models

lemonade list

Моя первая SLM

Это моя первая небольшая языковая модель, обученная с нуля на собственном датасете, созданном из истории моей переписки с другом.

Характеристики

Архитектура: decoder-only Transformer
Количество параметров: ~1 миллион
Размер контекста: 256 токенов
Язык: русский
Обучение: с нуля, без использования предобученных весов
Обработано за всё обучение: ~95,8 миллиона токенов
Размер уникального корпуса: ~562 тысячи токенов

Модель предназначена для генерации коротких сообщений и имитации стиля общения из исходной переписки.

В дальнейшем планируется дообучение на прочих датасетах, чтобы это была полноценная нейросеть, а не генератор чуши

Downloads last month: 14

GGUF

Model size

1.02M params

Architecture

llama

Hardware compatibility

32-bit

Collection including ChessVania/salgrai-alpha-v1

Alpha versions

Collection

Первые версии моделей • 1 item • Updated 9 days ago