Instructions to use 88plug/MiniCPM-o-4.5-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 88plug/MiniCPM-o-4.5-W4A16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="88plug/MiniCPM-o-4.5-W4A16", 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("88plug/MiniCPM-o-4.5-W4A16", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 88plug/MiniCPM-o-4.5-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "88plug/MiniCPM-o-4.5-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "88plug/MiniCPM-o-4.5-W4A16",
		"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/88plug/MiniCPM-o-4.5-W4A16

SGLang

How to use 88plug/MiniCPM-o-4.5-W4A16 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 "88plug/MiniCPM-o-4.5-W4A16" \
    --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": "88plug/MiniCPM-o-4.5-W4A16",
		"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 "88plug/MiniCPM-o-4.5-W4A16" \
        --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": "88plug/MiniCPM-o-4.5-W4A16",
		"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 88plug/MiniCPM-o-4.5-W4A16 with Docker Model Runner:
```
docker model run hf.co/88plug/MiniCPM-o-4.5-W4A16
```

MiniCPM-o-4.5-W4A16 / config.json

88plug-bot

Add config.json

96d49d4 verified 19 days ago

Raw

History Blame Contribute Delete

8.23 kB

	{
	"architectures": [
	"MiniCPMO"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"audio_chunk_length": 1.0,
	"audio_config": {
	"_attn_implementation_autoset": true,
	"_name_or_path": "openai/whisper-medium",
	"activation_dropout": 0.0,
	"activation_function": "gelu",
	"apply_spec_augment": false,
	"architectures": [
	"MiniCPMWhisperEncoder"
	],
	"attention_dropout": 0.0,
	"begin_suppress_tokens": [
	220,
	50257
	],
	"bos_token_id": 50257,
	"classifier_proj_size": 256,
	"d_model": 1024,
	"decoder_attention_heads": 16,
	"decoder_ffn_dim": 4096,
	"decoder_layerdrop": 0.0,
	"decoder_layers": 24,
	"decoder_start_token_id": 50258,
	"dropout": 0.0,
	"dtype": "float32",
	"encoder_attention_heads": 16,
	"encoder_ffn_dim": 4096,
	"encoder_layerdrop": 0.0,
	"encoder_layers": 24,
	"eos_token_id": 50257,
	"forced_decoder_ids": [
	[
	1,
	50259
	],
	[
	2,
	50359
	],
	[
	3,
	50363
	]
	],
	"init_std": 0.02,
	"mask_feature_length": 10,
	"mask_feature_min_masks": 0,
	"mask_feature_prob": 0.0,
	"mask_time_length": 10,
	"mask_time_min_masks": 2,
	"mask_time_prob": 0.05,
	"max_source_positions": 1500,
	"max_target_positions": 448,
	"median_filter_width": 7,
	"model_type": "whisper",
	"num_mel_bins": 80,
	"pad_token_id": 50257,
	"scale_embedding": false,
	"suppress_tokens": [
	1,
	2,
	7,
	8,
	9,
	10,
	14,
	25,
	26,
	27,
	28,
	29,
	31,
	58,
	59,
	60,
	61,
	62,
	63,
	90,
	91,
	92,
	93,
	359,
	503,
	522,
	542,
	873,
	893,
	902,
	918,
	922,
	931,
	1350,
	1853,
	1982,
	2460,
	2627,
	3246,
	3253,
	3268,
	3536,
	3846,
	3961,
	4183,
	4667,
	6585,
	6647,
	7273,
	9061,
	9383,
	10428,
	10929,
	11938,
	12033,
	12331,
	12562,
	13793,
	14157,
	14635,
	15265,
	15618,
	16553,
	16604,
	18362,
	18956,
	20075,
	21675,
	22520,
	26130,
	26161,
	26435,
	28279,
	29464,
	31650,
	32302,
	32470,
	36865,
	42863,
	47425,
	49870,
	50254,
	50258,
	50358,
	50359,
	50360,
	50361,
	50362
	],
	"tie_word_embeddings": true,
	"use_cache": true,
	"use_weighted_layer_sum": false,
	"vocab_size": 51865
	},
	"audio_pool_step": 5,
	"auto_map": {
	"AutoConfig": "configuration_minicpmo.MiniCPMOConfig",
	"AutoModel": "modeling_minicpmo.MiniCPMO",
	"AutoModelForCausalLM": "modeling_minicpmo.MiniCPMO"
	},
	"batch_vision_input": true,
	"bos_token_id": 151643,
	"drop_vision_last_layer": false,
	"dtype": "bfloat16",
	"eos_token_id": 151645,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"image_size": 448,
	"init_audio": true,
	"init_tts": true,
	"init_vision": true,
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"listen_speak_type": "asr",
	"max_position_embeddings": 40960,
	"max_window_layers": 36,
	"model_type": "minicpmo",
	"num_attention_heads": 32,
	"num_hidden_layers": 36,
	"num_key_value_heads": 8,
	"pad_token_id": null,
	"patch_size": 14,
	"query_num": 64,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"rope_theta": 1000000,
	"rope_type": "default"
	},
	"slice_config": {
	"max_slice_nums": 1,
	"model_type": "minicpmv",
	"patch_size": 14,
	"scale_resolution": 448
	},
	"slice_mode": true,
	"sliding_window": null,
	"stream_input": true,
	"tie_word_embeddings": false,
	"transformers_version": "5.12.1",
	"tts_config": {
	"_attn_implementation_autoset": true,
	"attention_type": "full_attention",
	"attn_implementation": "eager",
	"audio_bos_token_id": 151687,
	"audio_tokenizer_sample_rate": 16000,
	"audio_tokenizer_type": "s3tokenizer",
	"aug_layer_loss_weight": false,
	"aug_loss_weight": false,
	"backbone_model": "llama",
	"condition_type": "hidden_text_merge",
	"cosyvoice_config_path": null,
	"cosyvoice_model_dir": null,
	"filter_tts_loss": false,
	"hidden_act": "silu",
	"hidden_size": 768,
	"interleaved": false,
	"intermediate_size": 3072,
	"llm_dim": 4096,
	"llm_dim_model_base": 256,
	"llm_down_scale": false,
	"llm_hidden_size": 4096,
	"llm_intermediate_size": 768,
	"long_weight": 0.1,
	"max_position_embeddings": 4096,
	"model_type": "minicpmtts",
	"normalize_projected_hidden": true,
	"num_attention_heads": 12,
	"num_audio_tokens": 6562,
	"num_hidden_layers": 20,
	"num_key_value_heads": 12,
	"num_mel_bins": 100,
	"num_text_tokens": 152064,
	"num_vq": 1,
	"projector_type": "mlp",
	"recomputed_chunks": 1,
	"s3_stream_chunk_size": 25,
	"s3_stream_generate": false,
	"s3_stream_n_timesteps": 10,
	"s3_stream_prelook_size": 3,
	"short_weight": 0.1,
	"streaming": false,
	"streaming_audio_chunk_size": 50,
	"streaming_sliding_window": false,
	"streaming_sliding_window_audio_frame_rate": 50,
	"streaming_sliding_window_audio_init_text_length": 10,
	"streaming_sliding_window_audio_window_size": 300,
	"streaming_sliding_window_average_speed": 5,
	"streaming_sliding_window_fast_speed": 7,
	"streaming_sliding_window_max_text_len": 500,
	"streaming_sliding_window_slow_speed": 3,
	"streaming_sliding_window_text_window_size": 50,
	"streaming_text_chunk_max": 7,
	"streaming_text_chunk_min": 3,
	"streaming_text_reserved_len": 300,
	"text_eos_token_id": 151692,
	"tts_filter_loss_fix": false,
	"use_llm_hidden_state": false,
	"use_text": true,
	"window_size": 2
	},
	"use_cache": true,
	"use_image_id": true,
	"use_sliding_window": false,
	"version": "4.5",
	"vision_batch_size": 16,
	"vision_config": {
	"_attn_implementation_autoset": true,
	"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": "siglip_vision_model",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 27,
	"patch_size": 14
	},
	"vocab_size": 151748,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"format": "pack-quantized",
	"input_activations": null,
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": 128,
	"num_bits": 4,
	"observer": "memoryless_minmax",
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "group",
	"symmetric": true,
	"type": "int",
	"zp_dtype": null
	}
	}
	},
	"format": "pack-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"lm_head"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.17.2.a20260626"
	}
	}