Instructions to use second-state/C4AI-Command-R-v01-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/C4AI-Command-R-v01-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="second-state/C4AI-Command-R-v01-GGUF", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("second-state/C4AI-Command-R-v01-GGUF", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("second-state/C4AI-Command-R-v01-GGUF", trust_remote_code=True)

llama-cpp-python

How to use second-state/C4AI-Command-R-v01-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="second-state/C4AI-Command-R-v01-GGUF",
	filename="c4ai-command-r-v01-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use second-state/C4AI-Command-R-v01-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf second-state/C4AI-Command-R-v01-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/C4AI-Command-R-v01-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 second-state/C4AI-Command-R-v01-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/C4AI-Command-R-v01-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 second-state/C4AI-Command-R-v01-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/C4AI-Command-R-v01-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 second-state/C4AI-Command-R-v01-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/C4AI-Command-R-v01-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/C4AI-Command-R-v01-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/C4AI-Command-R-v01-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "second-state/C4AI-Command-R-v01-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": "second-state/C4AI-Command-R-v01-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/second-state/C4AI-Command-R-v01-GGUF:Q4_K_M

SGLang

How to use second-state/C4AI-Command-R-v01-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "second-state/C4AI-Command-R-v01-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/C4AI-Command-R-v01-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "second-state/C4AI-Command-R-v01-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/C4AI-Command-R-v01-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use second-state/C4AI-Command-R-v01-GGUF with Ollama:
```
ollama run hf.co/second-state/C4AI-Command-R-v01-GGUF:Q4_K_M
```

Unsloth Studio new

How to use second-state/C4AI-Command-R-v01-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 second-state/C4AI-Command-R-v01-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 second-state/C4AI-Command-R-v01-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for second-state/C4AI-Command-R-v01-GGUF to start chatting

Docker Model Runner
How to use second-state/C4AI-Command-R-v01-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/C4AI-Command-R-v01-GGUF:Q4_K_M
```

Lemonade

How to use second-state/C4AI-Command-R-v01-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/C4AI-Command-R-v01-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.C4AI-Command-R-v01-GGUF-Q4_K_M

List all available models

lemonade list

Xin Liu commited on Mar 19, 2024

Commit

d37d4c8

1 Parent(s): eda80f2

Update

Browse files

Signed-off-by: Xin Liu <sam@secondstate.io>

Files changed (1) hide show

README.md +55 -1

README.md CHANGED Viewed

@@ -1,3 +1,57 @@
 ---
-license: apache-2.0
 ---

 ---
+base_model: CohereForAI/c4ai-command-r-v01
+inference: false
+library_name: transformers
+license: cc-by-nc-4.0
+model_creator: Cohere
+model_name: C4AI Command-R
+quantized_by: Second State Inc.
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- ja
+- ko
+- zh
+- ar
 ---
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+# C4AI-Command-R-v01-GGUF
+## Original Model
+[second-state/C4AI-Command-R-v01-GGUF](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF)
+## Run with LlamaEdge
+- LlamaEdge version: coming soon
+## Quantized GGUF Models
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [c4ai-command-r-v01-Q2_K.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q2_K.gguf)     | Q2_K   | 2 | 13.8 GB| smallest, significant quality loss - not recommended for most purposes |
+| [c4ai-command-r-v01-Q3_K_L.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q3_K_L.gguf) | Q3_K_L | 3 | 19.1 GB| small, substantial quality loss |
+| [c4ai-command-r-v01-Q3_K_M.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q3_K_M.gguf) | Q3_K_M | 3 | 17.6 GB| very small, high quality loss |
+| [c4ai-command-r-v01-Q3_K_S.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q3_K_S.gguf) | Q3_K_S | 3 | 15.9 GB| very small, high quality loss |
+| [c4ai-command-r-v01-Q4_0.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q4_0.gguf)     | Q4_0   | 4 | 20.2 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [c4ai-command-r-v01-Q4_K_M.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q4_K_M.gguf) | Q4_K_M | 4 | 21.5 GB| medium, balanced quality - recommended |
+| [c4ai-command-r-v01-Q4_K_S.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q4_K_S.gguf) | Q4_K_S | 4 | 20.4 GB| small, greater quality loss |
+| [c4ai-command-r-v01-Q5_0.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q5_0.gguf)     | Q5_0   | 5 | 24.3 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [c4ai-command-r-v01-Q5_K_M.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q5_K_M.gguf) | Q5_K_M | 5 | 25 GB| large, very low quality loss - recommended |
+| [c4ai-command-r-v01-Q5_K_S.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q5_K_S.gguf) | Q5_K_S | 5 | 24.3 GB| large, low quality loss - recommended |
+| [c4ai-command-r-v01-Q6_K.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q6_K.gguf)     | Q6_K   | 6 | 28.7 GB| very large, extremely low quality loss |
+| [c4ai-command-r-v01-Q8_0.gguf](https://huggingface.co/second-state/C4AI-Command-R-v01-GGUF/blob/main/c4ai-command-r-v01-Q8_0.gguf)     | Q8_0   | 8 | 37.2 GB| very large, extremely low quality loss - not recommended |
+*Quantized with llama.cpp b2450*