Instructions to use CohereLabs/North-Micro-Vision-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CohereLabs/North-Micro-Vision-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="CohereLabs/North-Micro-Vision-Instruct")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("CohereLabs/North-Micro-Vision-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("CohereLabs/North-Micro-Vision-Instruct", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CohereLabs/North-Micro-Vision-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CohereLabs/North-Micro-Vision-Instruct"
# 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/North-Micro-Vision-Instruct",
		"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/North-Micro-Vision-Instruct

SGLang

How to use CohereLabs/North-Micro-Vision-Instruct 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/North-Micro-Vision-Instruct" \
    --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/North-Micro-Vision-Instruct",
		"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/North-Micro-Vision-Instruct" \
        --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/North-Micro-Vision-Instruct",
		"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/North-Micro-Vision-Instruct with Docker Model Runner:
```
docker model run hf.co/CohereLabs/North-Micro-Vision-Instruct
```

North-Micro-Vision-Instruct / config.json

d-rau

Upload folder using huggingface_hub

4b0ecf6 verified 3 days ago

Raw

History Blame Contribute Delete

3.79 kB

	{
	"transformers_version": "5.15.0.dev0",
	"architectures": [
	"CohereCompassForConditionalGeneration"
	],
	"output_hidden_states": false,
	"return_dict": true,
	"dtype": "bfloat16",
	"chunk_size_feed_forward": 0,
	"is_encoder_decoder": false,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"problem_type": null,
	"text_config": {
	"architectures": null,
	"output_hidden_states": false,
	"return_dict": true,
	"dtype": "bfloat16",
	"chunk_size_feed_forward": 0,
	"is_encoder_decoder": false,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"problem_type": null,
	"vocab_size": 262144,
	"hidden_size": 2048,
	"intermediate_size": 6144,
	"logit_scale": 0.25,
	"num_hidden_layers": 28,
	"num_attention_heads": 16,
	"num_key_value_heads": 8,
	"hidden_act": "silu",
	"max_position_embeddings": 500000,
	"initializer_range": 0.02,
	"layer_norm_eps": 1e-05,
	"use_cache": true,
	"pad_token_id": 0,
	"bos_token_id": 2,
	"eos_token_id": 255001,
	"tie_word_embeddings": true,
	"rope_parameters": {
	"sliding_attention": {
	"mrope_interleaved": true,
	"mrope_section": [
	24,
	20,
	20
	],
	"rope_type": "default",
	"rope_theta": 50000
	},
	"full_attention": null,
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"attention_bias": false,
	"attention_dropout": 0.0,
	"sliding_window": 4096,
	"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"
	],
	"score_shift_a": null,
	"score_shift_b": null,
	"pooling": null,
	"head_dim": 128,
	"_name_or_path": "",
	"model_type": "cohere_compass_text",
	"output_attentions": false
	},
	"vision_config": {
	"architectures": null,
	"output_hidden_states": false,
	"return_dict": true,
	"dtype": "bfloat16",
	"chunk_size_feed_forward": 0,
	"is_encoder_decoder": false,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"problem_type": null,
	"depth": 27,
	"hidden_size": 1152,
	"hidden_act": "gelu_pytorch_tanh",
	"intermediate_size": 4304,
	"num_heads": 16,
	"in_channels": 3,
	"patch_size": 16,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2,
	"out_hidden_size": 2048,
	"num_position_embeddings": 2304,
	"deepstack_visual_indexes": [
	8,
	16,
	24
	],
	"initializer_range": 0.02,
	"_name_or_path": "",
	"model_type": "cohere_compass_vision",
	"output_attentions": false
	},
	"fusion_config": {
	"patch_embeddings": true
	},
	"image_token_id": 255031,
	"video_token_id": 255032,
	"vision_start_token_id": 255028,
	"vision_end_token_id": 255029,
	"tie_word_embeddings": true,
	"_name_or_path": "",
	"eos_token_id": 255001,
	"pad_token_id": 0,
	"model_type": "cohere_compass",
	"output_attentions": false
	}