Instructions to use modilify/Modilify-Mk2-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modilify/Modilify-Mk2-preview with Transformers:

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

pipe = pipeline("text-generation", model="modilify/Modilify-Mk2-preview", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("modilify/Modilify-Mk2-preview", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use modilify/Modilify-Mk2-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modilify/Modilify-Mk2-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-Mk2-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modilify/Modilify-Mk2-preview

SGLang

How to use modilify/Modilify-Mk2-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-Mk2-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-Mk2-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-Mk2-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-Mk2-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use modilify/Modilify-Mk2-preview with Docker Model Runner:
```
docker model run hf.co/modilify/Modilify-Mk2-preview
```

Modilify-Mk2-preview / README.md

ydy9038074

Publish Modilify Mk2 Preview step 1250 schema25

b88f761 verified 1 day ago

preview code

Raw History Blame Contribute Delete

2.12 kB

metadata

license: other
license_name: modilify-open-model-license-1.0
license_link: LICENSE
library_name: transformers
pipeline_tag: text-generation
tags:
  - diffusion
  - mixture-of-experts
  - trust-remote-code
  - safetensors

Modilify Mk2 Preview

PyTorch text inference for the step 1250, schema25 checkpoint migrated from Modilify-Mk2-preview-mlx. The model uses a shared DiffusionGemma text encoder/decoder, a rolling 256-token canvas, and dual-timescale GDN2 memory. The release contains 32 Safetensors shards totaling 48.23 GiB.

Dense and expert LoRA adapters remain unfused. Model loading preserves the 26 FP32 GDN2/norm parameters alongside BF16 weights. No vision tower is included.

Inference

Use Transformers 5.14.1, PyTorch, Accelerate, and Safetensors. Run from this directory or replace model_path with its location. Inference needs additional memory beyond the weights.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "."
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    trust_remote_code=True,
    dtype=torch.bfloat16,
    device_map="auto",
    attn_implementation="sdpa",
).eval()
inputs = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Explain why the sky is blue."}],
    tokenize=True,
    add_generation_prompt=True,
    enable_thinking=False,
    return_dict=True,
    return_tensors="pt",
).to(model.device)
output = model.generate(**inputs, max_new_tokens=128, seed=42)
print(tokenizer.decode(output.sequences[0, inputs.input_ids.shape[1]:],
                       skip_special_tokens=True))

For MPS, use device_map={"": "mps"}. Set enable_thinking=True in the chat template to request thinking. Generation uses temperature 0.8, top-k 40, min-p 0.05, target confidence 0.5, and failure budget 0.2. max_denoising_steps can bound generation. Static batches and continuous batching share the confidence-prefix commit policy; each request retains its own cache and RNG.