Instructions to use tripolskypetr/command_r_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tripolskypetr/command_r_gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tripolskypetr/command_r_gguf",
	filename="command_r.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 tripolskypetr/command_r_gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tripolskypetr/command_r_gguf
# Run inference directly in the terminal:
llama-cli -hf tripolskypetr/command_r_gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tripolskypetr/command_r_gguf
# Run inference directly in the terminal:
llama-cli -hf tripolskypetr/command_r_gguf

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 tripolskypetr/command_r_gguf
# Run inference directly in the terminal:
./llama-cli -hf tripolskypetr/command_r_gguf

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 tripolskypetr/command_r_gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tripolskypetr/command_r_gguf

Use Docker

docker model run hf.co/tripolskypetr/command_r_gguf

LM Studio
Jan
Ollama
How to use tripolskypetr/command_r_gguf with Ollama:
```
ollama run hf.co/tripolskypetr/command_r_gguf
```

Unsloth Studio

How to use tripolskypetr/command_r_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 tripolskypetr/command_r_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 tripolskypetr/command_r_gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tripolskypetr/command_r_gguf to start chatting

Docker Model Runner
How to use tripolskypetr/command_r_gguf with Docker Model Runner:
```
docker model run hf.co/tripolskypetr/command_r_gguf
```

Lemonade

How to use tripolskypetr/command_r_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tripolskypetr/command_r_gguf

Run and chat with the model

lemonade run user.command_r_gguf-{{QUANT_TAG}}

List all available models

lemonade list

Published especially for agent-swarm-kit

Due to my job tasks I often need to write the AI chat bots. The agent-swarm-kit helps me to orchestrate thousands of chat sessions. So, check the link, It contains a lot of demos for tool calling!

Command R

Command R is a generative model optimized for long context tasks such as retrieval-augmented generation (RAG) and using external APIs and tools. As a model built for companies to implement at scale, Command R boasts:

Strong accuracy on RAG and Tool Use
Low latency, and high throughput
Longer 128k context
Strong capabilities across 10 key languages

There are currently two versions of Command R:

Original release tagged v0.1
August 2024 update tagged 08-2024

References

P.S. You will need at least 32GB of RAM and RTX 3060 16GB to run that model

Downloads last month: 1

GGUF

Model size

32B params

Architecture

command-r

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

tripolskypetr
/

command_r_gguf

Published especially for agent-swarm-kit

Command R

References

Datasets used to train tripolskypetr/command_r_gguf

Space using tripolskypetr/command_r_gguf 1