Instructions to use openbmb/MiniCPM-V-2_6-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM-V-2_6-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-2_6-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-2_6-GPTQ", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM-V-2_6-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-2_6-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-2_6-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-2_6-GPTQ

SGLang

How to use openbmb/MiniCPM-V-2_6-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-2_6-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-2_6-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-2_6-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-2_6-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-2_6-GPTQ with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-V-2_6-GPTQ
```

MiniCPM-V-2_6-GPTQ / config.json

tc-mb

Add files using upload-large-folder tool

9913ace verified 4 days ago

raw

history blame contribute delete

7.2 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": "",
	"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": 151666,
	"max_position_embeddings": 32768,
	"hidden_size": 3584,
	"intermediate_size": 18944,
	"num_hidden_layers": 28,
	"num_attention_heads": 28,
	"use_sliding_window": false,
	"sliding_window": null,
	"max_window_layers": 28,
	"num_key_value_heads": 4,
	"hidden_act": "silu",
	"initializer_range": 0.02,
	"rms_norm_eps": 1e-06,
	"rope_theta": 1000000.0,
	"rope_scaling": null,
	"attention_dropout": 0.0,
	"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"
	],
	"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": 151643,
	"pad_token_id": null,
	"eos_token_id": 151645,
	"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-2_6",
	"transformers_version": "4.57.6",
	"version": 2.6,
	"auto_map": {
	"AutoConfig": "configuration_minicpm.MiniCPMVConfig",
	"AutoModel": "modeling_minicpmv.MiniCPMV",
	"AutoModelForCausalLM": "modeling_minicpmv.MiniCPMV"
	},
	"model_type": "minicpmv",
	"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
	}
	}