Instructions to use FastFlowLM/MiniCPM-V-4.7-1B-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FastFlowLM/MiniCPM-V-4.7-1B-NPU2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="FastFlowLM/MiniCPM-V-4.7-1B-NPU2")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("FastFlowLM/MiniCPM-V-4.7-1B-NPU2")
model = AutoModelForMultimodalLM.from_pretrained("FastFlowLM/MiniCPM-V-4.7-1B-NPU2", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FastFlowLM/MiniCPM-V-4.7-1B-NPU2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FastFlowLM/MiniCPM-V-4.7-1B-NPU2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FastFlowLM/MiniCPM-V-4.7-1B-NPU2",
		"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/FastFlowLM/MiniCPM-V-4.7-1B-NPU2

SGLang

How to use FastFlowLM/MiniCPM-V-4.7-1B-NPU2 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 "FastFlowLM/MiniCPM-V-4.7-1B-NPU2" \
    --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": "FastFlowLM/MiniCPM-V-4.7-1B-NPU2",
		"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 "FastFlowLM/MiniCPM-V-4.7-1B-NPU2" \
        --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": "FastFlowLM/MiniCPM-V-4.7-1B-NPU2",
		"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 FastFlowLM/MiniCPM-V-4.7-1B-NPU2 with Docker Model Runner:
```
docker model run hf.co/FastFlowLM/MiniCPM-V-4.7-1B-NPU2
```

MiniCPM-V-4.7-1B-NPU2 / config.json

FastFlowLM

Update config.json

8530134 verified 4 days ago

Raw History Blame Contribute Delete

2.88 kB

{
  "architectures": [
    "MiniCPMV4_7ForConditionalGeneration"
  ],
  "model_type": "minicpmv4_7",
  "flm_version": "1.0.13",
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_output_gate": true,
  "dtype": "bfloat16",
  "bos_token_id": 248045,
  "eos_token_id": 248044,
  "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": 1,
  "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,
  "tie_word_embeddings": false,
  "use_cache": true,
  "vocab_size": 248094,
  "rope_parameters": {
    "mrope_interleaved": true,
    "mrope_section": [
      11,
      11,
      10
    ],
    "rope_type": "default",
    "rope_theta": 10000000,
    "partial_rotary_factor": 0.25
  },
  "addr_qk": 53248,
  "addr_kv": 53536,
  "vision_model_weight": "vision_weight.q4nx",
  "image_token_id": 248056,
  "video_token_id": 248057,
  "insert_layer_id": 6,
  "downsample_mode": "16x",
  "mrope_mode": "canvas",
  "vision_config": {
    "MINICPM_V_PATCH_SIZE": 14,
    "MINICPM_V_IMAGE_SIZE": 980,
    "MINICPM_V_MAX_SLICE_NUMS": 9,
    "MINICPM_V_INSERT_LAYER_ID": 6,
    "MINICPM_V_SPATIAL_MERGE_SIZE": 2,
    "MINICPM_V_TEMPORAL_PATCH_SIZE": 1,
    "MINICPM_V_DOWNSAMPLE_FACTOR": 16,
    "MINICPM_V_VISION_RESCALE_FACTOR": 0.00392156862745098,
    "MINICPM_V_VISION_RESCALE_IMAGE_MEAN": 0.5,
    "MINICPM_V_VISION_RESCALE_IMAGE_STD": 0.5,
    "MINICPM_V_VISION_EMBED_DIM": 1152,
    "MINICPM_V_VISION_NUM_HEADS": 16,
    "MINICPM_V_VISION_HEAD_DIM": 72,
    "MINICPM_V_VISION_MLP_INTERMEDIATE_SIZE": 4304,
    "MINICPM_V_VISION_NUM_POSITION_EMBEDDINGS": 4900,
    "MINICPM_V_VISION_NUM_LAYERS": 27,
    "MINICPM_V_VISION_LAYER_NORM_EPSILON": 1e-06,
    "MINICPM_V_VISION_OUT_HIDDEN_SIZE": 1024,
    "MINICPM_V_MERGER_HIDDEN_SIZE": 4608,
    "MINICPM_V_VIT_MERGER_INTERMEDIATE_SIZE": 17216
  }
}

	{
	"architectures": [
	"MiniCPMV4_7ForConditionalGeneration"
	],
	"model_type": "minicpmv4_7",
	"flm_version": "1.0.13",
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"dtype": "bfloat16",
	"bos_token_id": 248045,
	"eos_token_id": 248044,
	"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": 1,
	"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,
	"tie_word_embeddings": false,
	"use_cache": true,
	"vocab_size": 248094,
	"rope_parameters": {
	"mrope_interleaved": true,
	"mrope_section": [
	11,
	11,
	10
	],
	"rope_type": "default",
	"rope_theta": 10000000,
	"partial_rotary_factor": 0.25
	},
	"addr_qk": 53248,
	"addr_kv": 53536,
	"vision_model_weight": "vision_weight.q4nx",
	"image_token_id": 248056,
	"video_token_id": 248057,
	"insert_layer_id": 6,
	"downsample_mode": "16x",
	"mrope_mode": "canvas",
	"vision_config": {
	"MINICPM_V_PATCH_SIZE": 14,
	"MINICPM_V_IMAGE_SIZE": 980,
	"MINICPM_V_MAX_SLICE_NUMS": 9,
	"MINICPM_V_INSERT_LAYER_ID": 6,
	"MINICPM_V_SPATIAL_MERGE_SIZE": 2,
	"MINICPM_V_TEMPORAL_PATCH_SIZE": 1,
	"MINICPM_V_DOWNSAMPLE_FACTOR": 16,
	"MINICPM_V_VISION_RESCALE_FACTOR": 0.00392156862745098,
	"MINICPM_V_VISION_RESCALE_IMAGE_MEAN": 0.5,
	"MINICPM_V_VISION_RESCALE_IMAGE_STD": 0.5,
	"MINICPM_V_VISION_EMBED_DIM": 1152,
	"MINICPM_V_VISION_NUM_HEADS": 16,
	"MINICPM_V_VISION_HEAD_DIM": 72,
	"MINICPM_V_VISION_MLP_INTERMEDIATE_SIZE": 4304,
	"MINICPM_V_VISION_NUM_POSITION_EMBEDDINGS": 4900,
	"MINICPM_V_VISION_NUM_LAYERS": 27,
	"MINICPM_V_VISION_LAYER_NORM_EPSILON": 1e-06,
	"MINICPM_V_VISION_OUT_HIDDEN_SIZE": 1024,
	"MINICPM_V_MERGER_HIDDEN_SIZE": 4608,
	"MINICPM_V_VIT_MERGER_INTERMEDIATE_SIZE": 17216
	}
	}