Instructions to use Vikhrmodels/it-5.2-fp16-cp-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vikhrmodels/it-5.2-fp16-cp-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Vikhrmodels/it-5.2-fp16-cp-GGUF",
	filename="it-5.2-fp16-cp-F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Vikhrmodels/it-5.2-fp16-cp-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Vikhrmodels/it-5.2-fp16-cp-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Vikhrmodels/it-5.2-fp16-cp-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Vikhrmodels/it-5.2-fp16-cp-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Vikhrmodels/it-5.2-fp16-cp-GGUF: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 Vikhrmodels/it-5.2-fp16-cp-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Vikhrmodels/it-5.2-fp16-cp-GGUF: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 Vikhrmodels/it-5.2-fp16-cp-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Vikhrmodels/it-5.2-fp16-cp-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Vikhrmodels/it-5.2-fp16-cp-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Vikhrmodels/it-5.2-fp16-cp-GGUF with Ollama:
```
ollama run hf.co/Vikhrmodels/it-5.2-fp16-cp-GGUF:Q4_K_M
```

Unsloth Studio

How to use Vikhrmodels/it-5.2-fp16-cp-GGUF 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 Vikhrmodels/it-5.2-fp16-cp-GGUF 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 Vikhrmodels/it-5.2-fp16-cp-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Vikhrmodels/it-5.2-fp16-cp-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Vikhrmodels/it-5.2-fp16-cp-GGUF with Docker Model Runner:
```
docker model run hf.co/Vikhrmodels/it-5.2-fp16-cp-GGUF:Q4_K_M
```

Lemonade

How to use Vikhrmodels/it-5.2-fp16-cp-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Vikhrmodels/it-5.2-fp16-cp-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.it-5.2-fp16-cp-GGUF-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Релиз вихря 0.5

Долили сильно больше данных в sft, теперь стабильнее работает json и multiturn, слегка подточили параметры претрена модели

Added a lot more data to sft, now json and multiturn work more stable on long context and hard prompts


@article{nikolich2024vikhr,
  title={Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian},
  author={Aleksandr Nikolich and Konstantin Korolev and Artem Shelmanov},
  journal={arXiv preprint arXiv:2405.13929},
  year={2024},
  url={https://arxiv.org/pdf/2405.13929}
}

Downloads last month: 189

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for Vikhrmodels/it-5.2-fp16-cp-GGUF

Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian

Paper • 2405.13929 • Published May 22, 2024 • 55