Instructions to use DBMe/command-r-plus-3.2bpw-h6-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DBMe/command-r-plus-3.2bpw-h6-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="DBMe/command-r-plus-3.2bpw-h6-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DBMe/command-r-plus-3.2bpw-h6-exl2")
model = AutoModelForCausalLM.from_pretrained("DBMe/command-r-plus-3.2bpw-h6-exl2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DBMe/command-r-plus-3.2bpw-h6-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DBMe/command-r-plus-3.2bpw-h6-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DBMe/command-r-plus-3.2bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DBMe/command-r-plus-3.2bpw-h6-exl2

SGLang

How to use DBMe/command-r-plus-3.2bpw-h6-exl2 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 "DBMe/command-r-plus-3.2bpw-h6-exl2" \
    --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": "DBMe/command-r-plus-3.2bpw-h6-exl2",
		"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 "DBMe/command-r-plus-3.2bpw-h6-exl2" \
        --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": "DBMe/command-r-plus-3.2bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DBMe/command-r-plus-3.2bpw-h6-exl2 with Docker Model Runner:
```
docker model run hf.co/DBMe/command-r-plus-3.2bpw-h6-exl2
```

Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

Quantized model => https://huggingface.co/CohereForAI/c4ai-command-r-plus

Quantization Details:
Quantization is done using turboderp's ExLlamaV2 v0.2.2.

I use the default calibration datasets and arguments. The repo also includes a "measurement.json" file, which was used during the quantization process.

For models with bits per weight (BPW) over 6.0, I default to quantizing the lm_head layer at 8 bits instead of the standard 6 bits.

Who are you? What's with these weird BPWs on [insert model here]?
I specialize in optimized EXL2 quantization for models in the 70B to 100B+ range, specifically tailored for 48GB VRAM setups. My rig is built using 2 x 3090s with a Ryzen APU (APU used solely for desktop output—no VRAM wasted on the 3090s). I use TabbyAPI for inference, targeting context sizes between 32K and 64K.

Every model I upload includes a config.yml file with my ideal TabbyAPI settings. If you're using my config, don’t forget to set PYTORCH_CUDA_ALLOC_CONF=backend:cudaMallocAsync to save some VRAM.

Downloads last month: 5