Instructions to use mlx-community/DeepSeek-OCR-2-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/DeepSeek-OCR-2-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="mlx-community/DeepSeek-OCR-2-4bit", trust_remote_code=True)
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 AutoModel
model = AutoModel.from_pretrained("mlx-community/DeepSeek-OCR-2-4bit", trust_remote_code=True, device_map="auto")

MLX

How to use mlx-community/DeepSeek-OCR-2-4bit with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("mlx-community/DeepSeek-OCR-2-4bit")
config = load_config("mlx-community/DeepSeek-OCR-2-4bit")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use mlx-community/DeepSeek-OCR-2-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/DeepSeek-OCR-2-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/DeepSeek-OCR-2-4bit",
		"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/mlx-community/DeepSeek-OCR-2-4bit

SGLang

How to use mlx-community/DeepSeek-OCR-2-4bit 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 "mlx-community/DeepSeek-OCR-2-4bit" \
    --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": "mlx-community/DeepSeek-OCR-2-4bit",
		"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 "mlx-community/DeepSeek-OCR-2-4bit" \
        --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": "mlx-community/DeepSeek-OCR-2-4bit",
		"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 mlx-community/DeepSeek-OCR-2-4bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/DeepSeek-OCR-2-4bit
```
Atomic Chat

DeepSeek-OCR-2-4bit / config.json

prince-canuma

Upload folder using huggingface_hub

378131e verified 8 months ago

Raw

History Blame Contribute Delete

3.27 kB

	{
	"architectures": [
	"DeepseekOCR2ForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "modeling_deepseekocr2.DeepseekOCR2Config",
	"AutoModel": "modeling_deepseekocr2.DeepseekOCR2ForCausalLM"
	},
	"bos_token_id": 0,
	"candidate_resolutions": [
	[
	1024,
	1024
	]
	],
	"eos_token_id": 1,
	"first_k_dense_replace": 1,
	"global_view_pos": "head",
	"hidden_size": 1280,
	"intermediate_size": 6848,
	"kv_lora_rank": null,
	"language_config": {
	"architectures": [
	"DeepseekV2ForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_deepseekv2.DeepseekV2Config",
	"AutoModel": "modeling_deepseek.DeepseekV2Model",
	"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
	},
	"bos_token_id": 0,
	"eos_token_id": 1,
	"first_k_dense_replace": 1,
	"hidden_size": 1280,
	"intermediate_size": 6848,
	"kv_lora_rank": null,
	"lm_head": true,
	"max_position_embeddings": 8192,
	"moe_intermediate_size": 896,
	"n_group": 1,
	"n_routed_experts": 64,
	"n_shared_experts": 2,
	"num_attention_heads": 10,
	"num_experts_per_tok": 6,
	"num_hidden_layers": 12,
	"num_key_value_heads": 10,
	"q_lora_rank": null,
	"qk_nope_head_dim": 0,
	"qk_rope_head_dim": 0,
	"rm_head": false,
	"topk_group": 1,
	"topk_method": "greedy",
	"torch_dtype": "bfloat16",
	"use_mla": false,
	"v_head_dim": 0,
	"vocab_size": 129280
	},
	"lm_head": true,
	"max_position_embeddings": 8192,
	"model_type": "deepseekocr_2",
	"moe_intermediate_size": 896,
	"n_group": 1,
	"n_routed_experts": 64,
	"n_shared_experts": 2,
	"num_attention_heads": 10,
	"num_experts_per_tok": 6,
	"num_hidden_layers": 12,
	"num_key_value_heads": 10,
	"projector_config": {
	"input_dim": 896,
	"model_type": "mlp_projector",
	"n_embed": 1280,
	"projector_type": "linear"
	},
	"q_lora_rank": null,
	"qk_nope_head_dim": 0,
	"qk_rope_head_dim": 0,
	"quantization": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"rm_head": false,
	"tile_tag": "2D",
	"topk_group": 1,
	"topk_method": "greedy",
	"transformers_version": "4.46.3",
	"use_mla": false,
	"v_head_dim": 0,
	"vision_config": {
	"image_size": 1024,
	"mlp_ratio": 3.7362,
	"model_name": "deepencoderv2",
	"model_type": "vision",
	"width": {
	"qwen2-0-5b": {
	"dim": 896
	},
	"sam_vit_b": {
	"downsample_channels": [
	512,
	1024
	],
	"global_attn_indexes": [
	2,
	5,
	8,
	11
	],
	"heads": 12,
	"layers": 12,
	"width": 768
	}
	}
	},
	"vocab_size": 129280
	}