Instructions to use gghfez/c4ai-command-a-03-2025-exl2-3bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gghfez/c4ai-command-a-03-2025-exl2-3bpw with Transformers:

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

pipe = pipeline("text-generation", model="gghfez/c4ai-command-a-03-2025-exl2-3bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gghfez/c4ai-command-a-03-2025-exl2-3bpw")
model = AutoModelForCausalLM.from_pretrained("gghfez/c4ai-command-a-03-2025-exl2-3bpw", 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 gghfez/c4ai-command-a-03-2025-exl2-3bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gghfez/c4ai-command-a-03-2025-exl2-3bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gghfez/c4ai-command-a-03-2025-exl2-3bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gghfez/c4ai-command-a-03-2025-exl2-3bpw

SGLang

How to use gghfez/c4ai-command-a-03-2025-exl2-3bpw 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 "gghfez/c4ai-command-a-03-2025-exl2-3bpw" \
    --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": "gghfez/c4ai-command-a-03-2025-exl2-3bpw",
		"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 "gghfez/c4ai-command-a-03-2025-exl2-3bpw" \
        --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": "gghfez/c4ai-command-a-03-2025-exl2-3bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gghfez/c4ai-command-a-03-2025-exl2-3bpw with Docker Model Runner:
```
docker model run hf.co/gghfez/c4ai-command-a-03-2025-exl2-3bpw
```

exl2 + cohere2 stable now?

by fizzacles - opened Oct 5, 2025

Discussion

fizzacles

Oct 5, 2025

I'm sorry for the confusion, i thought CMD-A's model architecture had some stability issues in exl2 format? Do you know if it's usable or stable now?

gghfez

Owner Oct 21, 2025

Hi, just noticed your message here.
Nope, Cohere2 models are still broken in exl2. It's been fixed in exllamav3 since v0.06 though, so I'd recommend this quant:

Downtown-Case/c4ai-command-a-03-2025-exl3-3.12bpw-hb6

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