Instructions to use pmysl/c4ai-command-r-plus-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use pmysl/c4ai-command-r-plus-GGUF 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 pmysl/c4ai-command-r-plus-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf pmysl/c4ai-command-r-plus-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pmysl/c4ai-command-r-plus-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf pmysl/c4ai-command-r-plus-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 pmysl/c4ai-command-r-plus-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf pmysl/c4ai-command-r-plus-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 pmysl/c4ai-command-r-plus-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pmysl/c4ai-command-r-plus-GGUF:Q4_K_M

Use Docker

docker model run hf.co/pmysl/c4ai-command-r-plus-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use pmysl/c4ai-command-r-plus-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pmysl/c4ai-command-r-plus-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pmysl/c4ai-command-r-plus-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pmysl/c4ai-command-r-plus-GGUF:Q4_K_M

Ollama
How to use pmysl/c4ai-command-r-plus-GGUF with Ollama:
```
ollama run hf.co/pmysl/c4ai-command-r-plus-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use pmysl/c4ai-command-r-plus-GGUF with Docker Model Runner:
```
docker model run hf.co/pmysl/c4ai-command-r-plus-GGUF:Q4_K_M
```

Lemonade

How to use pmysl/c4ai-command-r-plus-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pmysl/c4ai-command-r-plus-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.c4ai-command-r-plus-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

other quants available?

by veryVANYA - opened Apr 5, 2024

Discussion

veryVANYA

Apr 5, 2024

ty for uploading experimental so quick, curious if you've got the 4,5,6,8 as well

pmysl

Owner Apr 5, 2024

Yes, I'm just uploading them now

veryVANYA

Apr 5, 2024

got them ty, how did you load them in? i combined but not able to load on lm studio

luzamu

Apr 5, 2024

•

edited Apr 5, 2024

Will here be IQ quants? My potato server really need them😭. Whatever, thanks for all your work!

pmysl

Owner Apr 5, 2024

got them ty, how did you load them in? i combined but not able to load on lm studio

I built the llama.cpp fork mentioned in the readme and used it for inference. Combined weights won't work in LM Studio because the bundled llama.cpp version doesn't support them

Will here be IQ quants? My potato server really need them😭. Whatever, thanks for all your work!

If you're looking for IQ quants you can check this repo: https://huggingface.co/dranger003/c4ai-command-r-plus-iMat.GGUF

Kalemnor

Apr 6, 2024

Shouldn't the 2_K version be around 25GB? Why is it 40GB?

pmysl

Owner Apr 7, 2024

This is the effect of how Q2_K quantization works in llama.cpp. Not all tensors have Q2_K precision. In the image below, you can see what this looks like for the first block in the Q2_K model

Kalemnor

Apr 7, 2024

So 32 GB(16x2) VRAM are not enough without offloading some layers on the RAM.

pmysl

Owner Apr 7, 2024

•

edited Apr 7, 2024

Unfortunately, yes. If you want to move all layers to GPUs, check the imatrix quants (such as IQ2_XXS) from the dranger003/c4ai-command-r-plus-iMat.GGUF repo. They're smaller than 32 GB

Kalemnor

Apr 7, 2024

Thanks for the direction.

pmysl changed discussion status to closed Apr 8, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment