Instructions to use openbmb/MiniCPM-V-4-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM-V-4-GPTQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="openbmb/MiniCPM-V-4-GPTQ", 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("openbmb/MiniCPM-V-4-GPTQ", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM-V-4-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM-V-4-GPTQ"
# 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-V-4-GPTQ",
		"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-V-4-GPTQ

SGLang

How to use openbmb/MiniCPM-V-4-GPTQ 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-V-4-GPTQ" \
    --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-V-4-GPTQ",
		"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-V-4-GPTQ" \
        --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-V-4-GPTQ",
		"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-V-4-GPTQ with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-V-4-GPTQ
```

MiniCPM-V-4-GPTQ / config.json

tc-mb

Add files using upload-large-folder tool

eaf3614 verified 6 days ago

raw

history blame contribute delete

10 kB

	{
	"use_cache": true,
	"query_num": 64,
	"image_size": 448,
	"drop_vision_last_layer": false,
	"batch_vision_input": true,
	"use_image_id": true,
	"vision_batch_size": 16,
	"slice_config": {
	"return_dict": true,
	"output_hidden_states": false,
	"torchscript": false,
	"dtype": null,
	"pruned_heads": {},
	"tie_word_embeddings": true,
	"chunk_size_feed_forward": 0,
	"is_encoder_decoder": false,
	"is_decoder": false,
	"cross_attention_hidden_size": null,
	"add_cross_attention": false,
	"tie_encoder_decoder": false,
	"architectures": null,
	"finetuning_task": null,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"task_specific_params": null,
	"problem_type": null,
	"tokenizer_class": null,
	"prefix": null,
	"bos_token_id": null,
	"pad_token_id": null,
	"eos_token_id": null,
	"sep_token_id": null,
	"decoder_start_token_id": null,
	"max_length": 20,
	"min_length": 0,
	"do_sample": false,
	"early_stopping": false,
	"num_beams": 1,
	"temperature": 1.0,
	"top_k": 50,
	"top_p": 1.0,
	"typical_p": 1.0,
	"repetition_penalty": 1.0,
	"length_penalty": 1.0,
	"no_repeat_ngram_size": 0,
	"encoder_no_repeat_ngram_size": 0,
	"bad_words_ids": null,
	"num_return_sequences": 1,
	"output_scores": false,
	"return_dict_in_generate": false,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"remove_invalid_values": false,
	"exponential_decay_length_penalty": null,
	"suppress_tokens": null,
	"begin_suppress_tokens": null,
	"num_beam_groups": 1,
	"diversity_penalty": 0.0,
	"_name_or_path": "",
	"model_type": "minicpmv",
	"tf_legacy_loss": false,
	"use_bfloat16": false,
	"patch_size": 14,
	"max_slice_nums": 9,
	"scale_resolution": 448,
	"output_attentions": false
	},
	"slice_mode": true,
	"vision_config": {
	"return_dict": true,
	"output_hidden_states": false,
	"torchscript": false,
	"dtype": null,
	"pruned_heads": {},
	"tie_word_embeddings": true,
	"chunk_size_feed_forward": 0,
	"is_encoder_decoder": false,
	"is_decoder": false,
	"cross_attention_hidden_size": null,
	"add_cross_attention": false,
	"tie_encoder_decoder": false,
	"architectures": null,
	"finetuning_task": null,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"task_specific_params": null,
	"problem_type": null,
	"tokenizer_class": null,
	"prefix": null,
	"bos_token_id": null,
	"pad_token_id": null,
	"eos_token_id": null,
	"sep_token_id": null,
	"decoder_start_token_id": null,
	"max_length": 20,
	"min_length": 0,
	"do_sample": false,
	"early_stopping": false,
	"num_beams": 1,
	"temperature": 1.0,
	"top_k": 50,
	"top_p": 1.0,
	"typical_p": 1.0,
	"repetition_penalty": 1.0,
	"length_penalty": 1.0,
	"no_repeat_ngram_size": 0,
	"encoder_no_repeat_ngram_size": 0,
	"bad_words_ids": null,
	"num_return_sequences": 1,
	"output_scores": false,
	"return_dict_in_generate": false,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"remove_invalid_values": false,
	"exponential_decay_length_penalty": null,
	"suppress_tokens": null,
	"begin_suppress_tokens": null,
	"num_beam_groups": 1,
	"diversity_penalty": 0.0,
	"_name_or_path": "",
	"_attn_implementation_autoset": true,
	"model_type": "siglip_vision_model",
	"tf_legacy_loss": false,
	"use_bfloat16": false,
	"hidden_size": 1152,
	"intermediate_size": 4304,
	"num_hidden_layers": 27,
	"num_attention_heads": 16,
	"num_channels": 3,
	"patch_size": 14,
	"image_size": 980,
	"attention_dropout": 0.0,
	"layer_norm_eps": 1e-06,
	"hidden_act": "gelu_pytorch_tanh",
	"output_attentions": false
	},
	"patch_size": 14,
	"vocab_size": 73448,
	"max_position_embeddings": 32768,
	"hidden_size": 2560,
	"intermediate_size": 10240,
	"num_hidden_layers": 32,
	"num_attention_heads": 32,
	"num_key_value_heads": 2,
	"hidden_act": "silu",
	"initializer_range": 0.1,
	"rms_norm_eps": 1e-06,
	"pretraining_tp": 1,
	"rope_theta": 10000.0,
	"rope_scaling": {
	"factor": 1.0,
	"long_factor": [
	0.9977997200264581,
	1.014658295992452,
	1.0349680404997148,
	1.059429246056193,
	1.0888815016813513,
	1.1243301355211495,
	1.166977103606075,
	1.2182568066927284,
	1.2798772354275727,
	1.3538666751582975,
	1.4426259039919596,
	1.5489853358570191,
	1.6762658237220625,
	1.8283407612492941,
	2.0096956085876183,
	2.225478927469756,
	2.481536379650452,
	2.784415934557119,
	3.1413289096347365,
	3.560047844772632,
	4.048719380066383,
	4.615569542115128,
	5.2684819496549835,
	6.014438591970396,
	6.858830049237097,
	7.804668263503327,
	8.851768731513417,
	9.99600492938444,
	11.228766118181639,
	12.536757560834843,
	13.902257701387796,
	15.303885189125953,
	16.717837610115794,
	18.119465097853947,
	19.484965238406907,
	20.792956681060105,
	22.02571786985731,
	23.16995406772833,
	24.217054535738416,
	25.16289275000465,
	26.007284207271347,
	26.753240849586767,
	27.40615325712662,
	27.973003419175363,
	28.461674954469114,
	28.880393889607006,
	29.237306864684626,
	29.540186419591297,
	29.79624387177199,
	30.01202719065413,
	30.193382037992453,
	30.34545697551969,
	30.47273746338473,
	30.579096895249787,
	30.66785612408345,
	30.741845563814174,
	30.80346599254902,
	30.85474569563567,
	30.897392663720595,
	30.932841297560394,
	30.962293553185553,
	30.986754758742034,
	31.007064503249293,
	31.02392307921529
	],
	"original_max_position_embeddings": 32786,
	"rope_type": "longrope",
	"short_factor": [
	0.9977997200264581,
	1.014658295992452,
	1.0349680404997148,
	1.059429246056193,
	1.0888815016813513,
	1.1243301355211495,
	1.166977103606075,
	1.2182568066927284,
	1.2798772354275727,
	1.3538666751582975,
	1.4426259039919596,
	1.5489853358570191,
	1.6762658237220625,
	1.8283407612492941,
	2.0096956085876183,
	2.225478927469756,
	2.481536379650452,
	2.784415934557119,
	3.1413289096347365,
	3.560047844772632,
	4.048719380066383,
	4.615569542115128,
	5.2684819496549835,
	6.014438591970396,
	6.858830049237097,
	7.804668263503327,
	8.851768731513417,
	9.99600492938444,
	11.228766118181639,
	12.536757560834843,
	13.902257701387796,
	15.303885189125953,
	16.717837610115794,
	18.119465097853947,
	19.484965238406907,
	20.792956681060105,
	22.02571786985731,
	23.16995406772833,
	24.217054535738416,
	25.16289275000465,
	26.007284207271347,
	26.753240849586767,
	27.40615325712662,
	27.973003419175363,
	28.461674954469114,
	28.880393889607006,
	29.237306864684626,
	29.540186419591297,
	29.79624387177199,
	30.01202719065413,
	30.193382037992453,
	30.34545697551969,
	30.47273746338473,
	30.579096895249787,
	30.66785612408345,
	30.741845563814174,
	30.80346599254902,
	30.85474569563567,
	30.897392663720595,
	30.932841297560394,
	30.962293553185553,
	30.986754758742034,
	31.007064503249293,
	31.02392307921529
	]
	},
	"attention_bias": false,
	"attention_dropout": 0.0,
	"mlp_bias": false,
	"head_dim": 128,
	"return_dict": true,
	"output_hidden_states": false,
	"torchscript": false,
	"dtype": "bfloat16",
	"pruned_heads": {},
	"tie_word_embeddings": false,
	"chunk_size_feed_forward": 0,
	"is_encoder_decoder": false,
	"is_decoder": false,
	"cross_attention_hidden_size": null,
	"add_cross_attention": false,
	"tie_encoder_decoder": false,
	"architectures": [
	"MiniCPMV"
	],
	"finetuning_task": null,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"task_specific_params": null,
	"problem_type": null,
	"tokenizer_class": null,
	"prefix": null,
	"bos_token_id": 1,
	"pad_token_id": 2,
	"eos_token_id": [
	2,
	73440
	],
	"sep_token_id": null,
	"decoder_start_token_id": null,
	"max_length": 20,
	"min_length": 0,
	"do_sample": false,
	"early_stopping": false,
	"num_beams": 1,
	"temperature": 1.0,
	"top_k": 50,
	"top_p": 1.0,
	"typical_p": 1.0,
	"repetition_penalty": 1.0,
	"length_penalty": 1.0,
	"no_repeat_ngram_size": 0,
	"encoder_no_repeat_ngram_size": 0,
	"bad_words_ids": null,
	"num_return_sequences": 1,
	"output_scores": false,
	"return_dict_in_generate": false,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"remove_invalid_values": false,
	"exponential_decay_length_penalty": null,
	"suppress_tokens": null,
	"begin_suppress_tokens": null,
	"num_beam_groups": 1,
	"diversity_penalty": 0.0,
	"_name_or_path": "/cache/shitong/autoGPTQ/models/MiniCPM-V-4",
	"transformers_version": "4.57.6",
	"auto_map": {
	"AutoConfig": "configuration_minicpm.MiniCPMVConfig",
	"AutoModel": "modeling_minicpmv.MiniCPMV",
	"AutoModelForCausalLM": "modeling_minicpmv.MiniCPMV"
	},
	"model_type": "minicpmv",
	"version": 4.0,
	"tf_legacy_loss": false,
	"use_bfloat16": false,
	"output_attentions": false,
	"quantization_config": {
	"bits": 4,
	"group_size": 128,
	"damp_percent": 0.01,
	"desc_act": false,
	"static_groups": false,
	"sym": true,
	"true_sequential": true,
	"quant_method": "gptq",
	"checkpoint_format": "gptq",
	"model_name_or_path": null,
	"model_file_base_name": null
	}
	}