Instructions to use CohereLabs/command-a-plus-05-2026-w4a4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CohereLabs/command-a-plus-05-2026-w4a4 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-w4a4")
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-w4a4")
model = AutoModelForImageTextToText.from_pretrained("CohereLabs/command-a-plus-05-2026-w4a4")
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
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CohereLabs/command-a-plus-05-2026-w4a4 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-w4a4"
# 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-w4a4",
		"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-w4a4

SGLang

How to use CohereLabs/command-a-plus-05-2026-w4a4 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-w4a4" \
    --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-w4a4",
		"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-w4a4" \
        --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-w4a4",
		"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-w4a4 with Docker Model Runner:
```
docker model run hf.co/CohereLabs/command-a-plus-05-2026-w4a4
```

Chat Completion "reasoning" support

by yzong-rh - opened 14 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-3

Files changed (1) hide show

chat_template.jinja +5 -3

chat_template.jinja CHANGED Viewed

@@ -125,8 +125,10 @@ These instructions serve as your defaults, but they can be overridden in subsequ
     {%- endif %}
 {%- endmacro %}
 {%- macro print_thinking(msg) %}
-    {%- if msg.thinking -%}
 {{ msg.thinking }}
     {%- elif msg.content and msg.content[0].thinking -%}
 {{ msg.content[0].thinking }}
     {%- endif %}
@@ -224,7 +226,7 @@ Your output should adhere to the following json schema:
             {% if not skip_thinking %}
                 {% if message.tool_plan -%}
                     <|START_THINKING|>{{ message.tool_plan }}<|END_THINKING|>
-                {%- elif message.thinking or (message.content and message.content[0].type == "thinking") -%}
                     <|START_THINKING|>{{ print_thinking(message) }}<|END_THINKING|>
                 {%- endif %}
             {%- endif %}<|START_ACTION|>[
@@ -236,7 +238,7 @@ Your output should adhere to the following json schema:
 ]<|END_ACTION|><|END_OF_TURN_TOKEN|>
         {%- else -%}
-            {% if (message.thinking or (message.content and message.content[0].type == "thinking")) and not skip_thinking -%}
                 <|START_THINKING|>{{ print_thinking(message) }}<|END_THINKING|>
             {%- endif -%}
             {{ print_msg(message) }}<|END_OF_TURN_TOKEN|>

     {%- endif %}
 {%- endmacro %}
 {%- macro print_thinking(msg) %}
+    {%- if msg.thinking is defined and msg.thinking is not none -%}
 {{ msg.thinking }}
+    {%- elif msg.reasoning is defined and msg.reasoning is not none -%}
+{{ msg.reasoning }}
     {%- elif msg.content and msg.content[0].thinking -%}
 {{ msg.content[0].thinking }}
     {%- endif %}
             {% if not skip_thinking %}
                 {% if message.tool_plan -%}
                     <|START_THINKING|>{{ message.tool_plan }}<|END_THINKING|>
+                {%- elif (message.thinking is defined and message.thinking is not none) or (message.reasoning is defined and message.reasoning is not none) or (message.content and message.content[0].type == "thinking") -%}
                     <|START_THINKING|>{{ print_thinking(message) }}<|END_THINKING|>
                 {%- endif %}
             {%- endif %}<|START_ACTION|>[
 ]<|END_ACTION|><|END_OF_TURN_TOKEN|>
         {%- else -%}
+            {% if ((message.thinking is defined and message.thinking is not none) or (message.reasoning is defined and message.reasoning is not none) or (message.content and message.content[0].type == "thinking")) and not skip_thinking -%}
                 <|START_THINKING|>{{ print_thinking(message) }}<|END_THINKING|>
             {%- endif -%}
             {{ print_msg(message) }}<|END_OF_TURN_TOKEN|>