Instructions to use CohereLabs/command-a-plus-05-2026-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CohereLabs/command-a-plus-05-2026-bf16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="CohereLabs/command-a-plus-05-2026-bf16")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("CohereLabs/command-a-plus-05-2026-bf16")
model = AutoModelForImageTextToText.from_pretrained("CohereLabs/command-a-plus-05-2026-bf16")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CohereLabs/command-a-plus-05-2026-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CohereLabs/command-a-plus-05-2026-bf16"
# 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/command-a-plus-05-2026-bf16",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/CohereLabs/command-a-plus-05-2026-bf16

SGLang

How to use CohereLabs/command-a-plus-05-2026-bf16 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/command-a-plus-05-2026-bf16" \
    --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/command-a-plus-05-2026-bf16",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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/command-a-plus-05-2026-bf16" \
        --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/command-a-plus-05-2026-bf16",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use CohereLabs/command-a-plus-05-2026-bf16 with Docker Model Runner:
```
docker model run hf.co/CohereLabs/command-a-plus-05-2026-bf16
```

command-a-plus-05-2026-bf16 / config.json

alexrs

Add files using upload-large-folder tool

e949b16 verified 1 day ago

raw

history blame contribute delete

4.25 kB

	{
	"adapter_layer_norm_eps": 1e-06,
	"alignment_activation_fn": "swiglu",
	"alignment_intermediate_size": 12288,
	"architectures": [
	"Cohere2VisionForConditionalGeneration"
	],
	"downsample_factor": 2,
	"dtype": "bfloat16",
	"enable_adapter_layer_norm": false,
	"image_token": 255031,
	"image_token_id": 255031,
	"max_splits_per_img": 12,
	"model_type": "cohere2_vision",
	"text_config": {
	"_sliding_window_pattern": 4,
	"add_cross_attention": false,
	"architectures": [
	"Cohere2MoeForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 2,
	"cross_attention_hidden_size": null,
	"decoder_start_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": 255001,
	"expert_selection_fn": "sigmoid",
	"finetuning_task": null,
	"first_k_dense_replace": 0,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"is_decoder": false,
	"layer_norm_eps": 1e-05,
	"layer_switch": 4,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"logit_scale": 1.0,
	"max_position_embeddings": 5000000,
	"model_type": "cohere2_moe",
	"norm_topk_prob": true,
	"num_attention_heads": 128,
	"num_experts": 128,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 32,
	"num_key_value_heads": 8,
	"num_shared_experts": 4,
	"order_of_interleaved_layers": "local_attn_first",
	"pad_token_id": 0,
	"position_embedding_type": "rope_gptj",
	"prefix": null,
	"prefix_dense_intermediate_size": 16384,
	"prefix_dense_sliding_window_pattern": 1,
	"pruned_heads": {},
	"rms_norm_eps": null,
	"rope_parameters": {
	"rope_theta": 50000,
	"rope_type": "default"
	},
	"rope_theta": 50000,
	"rotary_pct": 1.0,
	"sep_token_id": null,
	"shared_expert_combination_strategy": "average",
	"sliding_window": 4096,
	"task_specific_params": null,
	"tf_legacy_loss": false,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": true,
	"tokenizer_class": null,
	"torchscript": false,
	"use_bfloat16": false,
	"use_cache": true,
	"use_embedding_sharing": true,
	"use_gated_activation": true,
	"use_parallel_block": true,
	"use_parallel_embedding": false,
	"use_qk_norm": false,
	"vocab_size": 262144
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.8.0.dev0",
	"vision_config": {
	"add_cross_attention": false,
	"attention_dropout": 0.0,
	"bos_token_id": null,
	"cross_attention_hidden_size": null,
	"decoder_start_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": null,
	"finetuning_task": null,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"image_size": 512,
	"intermediate_size": 4304,
	"is_decoder": false,
	"layer_norm_eps": 1e-06,
	"model_type": "siglip_vision_model",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 27,
	"pad_token_id": null,
	"patch_size": 16,
	"prefix": null,
	"pruned_heads": {},
	"sep_token_id": null,
	"task_specific_params": null,
	"tf_legacy_loss": false,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": true,
	"tokenizer_class": null,
	"torchscript": false,
	"use_bfloat16": false,
	"vision_use_head": false
	},
	"vision_feature_layer": -1,
	"vision_feature_select_strategy": "full"
	}