Instructions to use modilify/Modilify-Mk1-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modilify/Modilify-Mk1-preview with Transformers:

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

pipe = pipeline("image-text-to-text", model="modilify/Modilify-Mk1-preview", 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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("modilify/Modilify-Mk1-preview", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use modilify/Modilify-Mk1-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modilify/Modilify-Mk1-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modilify/Modilify-Mk1-preview",
		"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/modilify/Modilify-Mk1-preview

SGLang

How to use modilify/Modilify-Mk1-preview 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 "modilify/Modilify-Mk1-preview" \
    --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": "modilify/Modilify-Mk1-preview",
		"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 "modilify/Modilify-Mk1-preview" \
        --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": "modilify/Modilify-Mk1-preview",
		"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 modilify/Modilify-Mk1-preview with Docker Model Runner:
```
docker model run hf.co/modilify/Modilify-Mk1-preview
```

Modilify-Mk1-preview / config.json

ydy9038074

Publish Modilify Mk1 Preview

164d101 verified 4 days ago

Raw

History Blame Contribute Delete

4.22 kB

	{
	"architectures": [
	"ModilifyMk1ForBlockDiffusion"
	],
	"auto_map": {
	"AutoConfig": "configuration_modilify_mk1.ModilifyMk1Config",
	"AutoModel": "modeling_modilify_mk1.ModilifyMk1Model",
	"AutoModelForCausalLM": "modeling_modilify_mk1.ModilifyMk1ForBlockDiffusion",
	"AutoModelForMultimodalLM": "modeling_modilify_mk1.ModilifyMk1ForBlockDiffusion"
	},
	"boi_token_id": 255999,
	"bos_token_id": 2,
	"canvas_length": 256,
	"commit_failure_budget": 0.2,
	"denoise_temperature": 0.8,
	"dtype": "bfloat16",
	"eoi_token_id": 258882,
	"eos_token_id": [
	1,
	106
	],
	"fused_entropy_weight": 0.5,
	"image_token_id": 258880,
	"initializer_range": 0.02,
	"jump_failure_budget": 2.0,
	"jump_on_no_progress_after": 12,
	"latent_dim": 1536,
	"latent_dropout": 0.0,
	"latent_local_attention_window": 128,
	"latent_memory_slots": 64,
	"latent_num_heads": 16,
	"latent_num_layers": 4,
	"max_ponder_steps": 64,
	"min_trajectory_progress": 0.005,
	"model_type": "modilify_mk1",
	"pad_token_id": 0,
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 2,
	"dtype": "bfloat16",
	"eos_token_id": 1,
	"final_logit_softcapping": 30.0,
	"global_head_dim": 512,
	"head_dim": 256,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 2816,
	"initializer_range": 0.02,
	"intermediate_size": 2112,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 262144,
	"model_type": "modilify_mk1_text",
	"moe_intermediate_size": 704,
	"num_attention_heads": 16,
	"num_experts": 128,
	"num_global_key_value_heads": 2,
	"num_hidden_layers": 30,
	"num_key_value_heads": 8,
	"pad_token_id": 0,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"full_attention": {
	"partial_rotary_factor": 0.25,
	"rope_theta": 1000000.0,
	"rope_type": "proportional"
	},
	"sliding_attention": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	}
	},
	"sliding_window": 1024,
	"tie_word_embeddings": true,
	"top_k_experts": 8,
	"use_bidirectional_attention": "vision",
	"vocab_size": 262144
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.14.1",
	"turn_end_token_id": 106,
	"vision_config": {
	"_name_or_path": "",
	"architectures": null,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"chunk_size_feed_forward": 0,
	"default_output_length": 280,
	"dtype": "bfloat16",
	"global_head_dim": 72,
	"head_dim": 72,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"intermediate_size": 4304,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"max_position_embeddings": 131072,
	"model_type": "gemma4_vision",
	"num_attention_heads": 16,
	"num_hidden_layers": 27,
	"num_key_value_heads": 16,
	"output_attentions": false,
	"output_hidden_states": false,
	"patch_size": 16,
	"pooling_kernel_size": 3,
	"position_embedding_size": 10240,
	"problem_type": null,
	"return_dict": true,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"rope_theta": 100.0,
	"rope_type": "default"
	},
	"standardize": true,
	"use_clipped_linears": false
	},
	"vocab_chunk_size": 65536
	}