Instructions to use openbmb/MiniCPM-OCR-1.0-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Local Apps Settings

How to use openbmb/MiniCPM-OCR-1.0-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM-OCR-1.0-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM-OCR-1.0-AWQ",
		"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/openbmb/MiniCPM-OCR-1.0-AWQ

SGLang

How to use openbmb/MiniCPM-OCR-1.0-AWQ 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 "openbmb/MiniCPM-OCR-1.0-AWQ" \
    --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": "openbmb/MiniCPM-OCR-1.0-AWQ",
		"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 "openbmb/MiniCPM-OCR-1.0-AWQ" \
        --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": "openbmb/MiniCPM-OCR-1.0-AWQ",
		"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 openbmb/MiniCPM-OCR-1.0-AWQ with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-OCR-1.0-AWQ
```

MiniCPM-OCR-1.0-AWQ / config.json

airlsyn

Update config.json

400ebd5 verified 6 days ago

Raw History Blame Contribute Delete

2.61 kB

{
  "architectures": [
    "MiniCPMOcrForConditionalGeneration"
  ],
  "downsample_mode": "4x",
  "model_type": "minicpm_ocr",
  "tie_word_embeddings": true,
  "transformers_version": "5.21.0",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 980,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "minicpm_ocr_vision",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "patch_size": 14
  },
  "insert_layer_id": 6,
  "image_token_id": 248056,
  "video_token_id": 248057,
  "dtype": "bfloat16",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_output_gate": true,
    "full_attention_interval": 4,
    "head_dim": 256,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 3584,
    "layer_types": [
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention"
    ],
    "linear_conv_kernel_dim": 4,
    "linear_key_head_dim": 128,
    "linear_num_key_heads": 16,
    "linear_num_value_heads": 16,
    "linear_value_head_dim": 128,
    "mamba_ssm_dtype": "float32",
    "max_position_embeddings": 262144,
    "mlp_only_layers": [],
    "mtp_num_hidden_layers": 0,
    "mtp_use_dedicated_embeddings": false,
    "num_attention_heads": 8,
    "num_hidden_layers": 24,
    "num_key_value_heads": 2,
    "partial_rotary_factor": 0.25,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "partial_rotary_factor": 0.25,
      "rope_theta": 10000000,
      "rope_type": "default"
    },
    "vocab_size": 248100,
    "model_type": "qwen3_5_text",
    "tie_word_embeddings": true
  },
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "modules_to_not_convert": [
      "in_proj_b",
      "in_proj_a",
      "model.vision_tower",
      "model.merger",
      "vpm",
      "vit_merger",
      "merger",
      "lm_head"
    ],
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true
  }
}

	{
	"architectures": [
	"MiniCPMOcrForConditionalGeneration"
	],
	"downsample_mode": "4x",
	"model_type": "minicpm_ocr",
	"tie_word_embeddings": true,
	"transformers_version": "5.21.0",
	"vision_config": {
	"attention_dropout": 0.0,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"image_size": 980,
	"intermediate_size": 4304,
	"layer_norm_eps": 1e-06,
	"model_type": "minicpm_ocr_vision",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 27,
	"patch_size": 14
	},
	"insert_layer_id": 6,
	"image_token_id": 248056,
	"video_token_id": 248057,
	"dtype": "bfloat16",
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"full_attention_interval": 4,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 1024,
	"initializer_range": 0.02,
	"intermediate_size": 3584,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention"
	],
	"linear_conv_kernel_dim": 4,
	"linear_key_head_dim": 128,
	"linear_num_key_heads": 16,
	"linear_num_value_heads": 16,
	"linear_value_head_dim": 128,
	"mamba_ssm_dtype": "float32",
	"max_position_embeddings": 262144,
	"mlp_only_layers": [],
	"mtp_num_hidden_layers": 0,
	"mtp_use_dedicated_embeddings": false,
	"num_attention_heads": 8,
	"num_hidden_layers": 24,
	"num_key_value_heads": 2,
	"partial_rotary_factor": 0.25,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"partial_rotary_factor": 0.25,
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"vocab_size": 248100,
	"model_type": "qwen3_5_text",
	"tie_word_embeddings": true
	},
	"quantization_config": {
	"bits": 4,
	"group_size": 128,
	"modules_to_not_convert": [
	"in_proj_b",
	"in_proj_a",
	"model.vision_tower",
	"model.merger",
	"vpm",
	"vit_merger",
	"merger",
	"lm_head"
	],
	"quant_method": "awq",
	"version": "gemm",
	"zero_point": true
	}
	}