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

Libraries

How to use CohereLabs/c4ai-command-a-03-2025 with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CohereLabs/c4ai-command-a-03-2025")
model = AutoModelForCausalLM.from_pretrained("CohereLabs/c4ai-command-a-03-2025")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CohereLabs/c4ai-command-a-03-2025 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/CohereLabs/c4ai-command-a-03-2025

SGLang

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

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

Question About VRAM Requirements for Full 256K Context Length

by mullerse - opened Mar 14, 2025

Discussion

mullerse

Mar 14, 2025

Dear CohereForAI Team,

first of all, thank you for your incredible work on the c4ai-command-a-03-2025 model. The advancements in context length and efficiency are truly impressive!

I am currently experimenting with the model using vLLM and have achieved a context length of approximately 110K tokens on 8 x RTX A6000 GPUs with the following settings:

#!/bin/bash
export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
export CUDA_LAUNCH_BLOCKING=0
export disable_custom_all_reduce=True

token=100000
python -m vllm.entrypoints.openai.api_server
--model=CohereForAI/c4ai-command-a-03-2025
--host 192.xxx.x.xx
--port 9000
--trust-remote-code
--device cuda
--tensor-parallel-size 8
--gpu-memory-utilization 1
--swap-space 10
--max_num_seqs 3
--max_num_batched_tokens $token
--max_model_len $token

According to the model card, the 256K token limit is theoretically achievable. However, I couldn’t find an explicit reference to the VRAM requirements needed to reach this full context length.

Could you provide any insights into how much GPU memory (VRAM) would be required to fully utilize 256K tokens? Would increasing the number of GPUs beyond 8x RTX A6000 significantly help, or is there another approach (e.g., CPU offloading, swap space tuning) that you would recommend?

Again, thank you for your fantastic work—this model is truly pushing boundaries! I appreciate any guidance you can share.

Best regards

freegheist

Mar 20, 2025

try reduce max_num_seqs=1 and set token size to multiple of 16

mullerse

Mar 22, 2025

Thank you very much for your reply!

Even with max_num_seqs=1, I still can’t load more tokens, and 100,000 is already a multiple of 16—yet 131,072 tokens don’t work either.
From my understanding, 8×48 GB (384 GB VRAM) should be enough for handling 256,000 tokens with this model, correct?

Thank you again for your assistance!

alexrs changed discussion status to closed Jun 12, 2025

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