Instructions to use yujiepan/diffusiongemma-moe-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/diffusiongemma-moe-tiny-random with Transformers:

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

pipe = pipeline("image-text-to-text", model="yujiepan/diffusiongemma-moe-tiny-random")
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("yujiepan/diffusiongemma-moe-tiny-random")
model = AutoModelForMultimodalLM.from_pretrained("yujiepan/diffusiongemma-moe-tiny-random", 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 yujiepan/diffusiongemma-moe-tiny-random with vLLM:

Install from pip and serve model

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

SGLang

How to use yujiepan/diffusiongemma-moe-tiny-random 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 "yujiepan/diffusiongemma-moe-tiny-random" \
    --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": "yujiepan/diffusiongemma-moe-tiny-random",
		"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 "yujiepan/diffusiongemma-moe-tiny-random" \
        --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": "yujiepan/diffusiongemma-moe-tiny-random",
		"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 yujiepan/diffusiongemma-moe-tiny-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/diffusiongemma-moe-tiny-random
```

diffusiongemma-moe-tiny-random / README.md

yujiepan

Duplicate from tiny-random/diffusiongemma-moe

6c7f24f 2 days ago

preview code

Raw History Blame Contribute Delete

21.1 kB

---
library_name: transformers
base_model:
- google/diffusiongemma-26B-A4B-it
---
This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [google/diffusiongemma-26B-A4B-it](https://huggingface.co/google/diffusiongemma-26B-A4B-it).

Structural comparison with `google/diffusiongemma-26B-A4B-it`:

| Feature | Source | Tiny |
|---|---:|---:|
| Input modalities | text, image, video | same |
| Vocabulary / tied embeddings | 262,144 / yes | same |
| Text layers | 30 | 12; two 5-sliding + 1-full cycles |
| Text width / local head dimension | 2,816 / 256 | 16 / 32 |
| Full-attention head dimension | 512 | 64 |
| MoE experts / active experts | 128 / 8 | 32 / 8 |
| Vision layers / width | 27 / 1,152 | 2 / 64 |
| Canvas length and self-conditioning | 256 / present | same |
| Stored precision | BF16 | BF16 |

The encoder/decoder weight sharing and the decoder self-conditioning branch are
provided by the native `DiffusionGemmaForBlockDiffusion` implementation rather
than serialized as independent copies.

| File path | Size |
|------|------|
| model.safetensors | 12.6MB |


### Example usage:

- Transformers (✅ verified)

```python
import numpy as np
import torch
from PIL import Image
from transformers import AutoProcessor, DiffusionGemmaForBlockDiffusion
from transformers.video_utils import VideoMetadata
model_id = "tiny-random/diffusiongemma-moe"
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.bfloat16 if device == "cuda" else torch.float32
model = DiffusionGemmaForBlockDiffusion.from_pretrained(model_id, dtype=dtype).to(device)
processor = AutoProcessor.from_pretrained(model_id)
image = Image.new("RGB", (64, 64), "red")
video = np.stack([np.asarray(Image.new("RGB", (64, 64), color)) for color in ("red", "green", "blue", "yellow")])
messages = [{"role": "user", "content": [
    {"type": "image", "image": image},
    {"type": "video", "video": video},
    {"type": "text", "text": "Describe the image and video."},
]}]
inputs = processor.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt",
    do_sample_frames=False,
    video_metadata=[VideoMetadata(total_num_frames=4, fps=2, frames_indices=[0, 1, 2, 3])],
).to(device)
output = model.generate(**inputs, max_new_tokens=10, max_denoising_steps=2)
print(processor.decode(output.sequences[0], skip_special_tokens=True)[-500:])
```

### Codes to create this repo (✅ verified):

<details><summary>Click to expand</summary>

```python
import json
from pathlib import Path
from shutil import copyfile
import torch
from huggingface_hub import hf_hub_download, list_repo_files
from transformers import AutoConfig, DiffusionGemmaForBlockDiffusion, set_seed
source_model_id = "google/diffusiongemma-26B-A4B-it"
save_folder = "/tmp/tiny-random/diffusiongemma-moe"
source_revision = "f7f5b7f5fa82ffc52addd066915886d497f5517b"
set_seed(42)
folder = Path(save_folder)
folder.mkdir(parents=True, exist_ok=True)
raw = json.loads(Path(hf_hub_download(source_model_id, "config.json", revision=source_revision)).read_text())
text = raw["text_config"]
text.update(
    hidden_size=16, head_dim=32, num_attention_heads=1, num_key_value_heads=1,
    intermediate_size=64, moe_intermediate_size=32, num_experts=32, top_k_experts=8,
    num_hidden_layers=12,
    layer_types=["sliding_attention"] * 5 + ["full_attention"] + ["sliding_attention"] * 5 + ["full_attention"],
    per_layer_config={"5": {"head_dim": 64, "num_key_value_heads": 1}, "11": {"head_dim": 64, "num_key_value_heads": 1}},
)
raw["vision_config"].update(
    hidden_size=64, intermediate_size=128, num_hidden_layers=2,
    num_attention_heads=2, num_key_value_heads=2, head_dim=32,
)
(folder / "config.json").write_text(json.dumps(raw, indent=2), encoding="utf-8")
config = AutoConfig.from_pretrained(folder)
model = DiffusionGemmaForBlockDiffusion(config).to(torch.bfloat16)
with torch.no_grad():
    for name, parameter in sorted(model.named_parameters()):
        if not parameter.is_floating_point():
            continue
        if name.endswith("norm.weight"):
            parameter.fill_(1)
        else:
            torch.nn.init.normal_(parameter, mean=0, std=0.02)
model.save_pretrained(folder, safe_serialization=True)
assets = {"chat_template.jinja", "generation_config.json", "model_index.json", "processor_config.json", "scheduler/scheduler_config.json", "tokenizer.json", "tokenizer_config.json"}
for filename in sorted(set(list_repo_files(source_model_id, revision=source_revision)) & assets):
    destination = folder / filename
    destination.parent.mkdir(parents=True, exist_ok=True)
    copyfile(hf_hub_download(source_model_id, filename, revision=source_revision), destination)
```

</details>

### Printing the model:

<details><summary>Click to expand</summary>

```text
DiffusionGemmaForBlockDiffusion(
  (model): DiffusionGemmaModel(
    (encoder): DiffusionGemmaEncoderModel(
      (language_model): DiffusionGemmaEncoderTextModel(
        (embed_tokens): DiffusionGemmaTextScaledWordEmbedding(262144, 16, padding_idx=0)
        (layers): ModuleList(
          (0-4): 5 x DiffusionGemmaEncoderTextLayer(
            (self_attn): DiffusionGemmaEncoderTextAttention(
              (q_proj): Linear(in_features=16, out_features=32, bias=False)
              (k_proj): Linear(in_features=16, out_features=32, bias=False)
              (v_proj): Linear(in_features=16, out_features=32, bias=False)
              (o_proj): Linear(in_features=32, out_features=16, bias=False)
              (q_norm): DiffusionGemmaRMSNorm()
              (k_norm): DiffusionGemmaRMSNorm()
              (v_norm): DiffusionGemmaRMSNorm()
            )
            (mlp): DiffusionGemmaText4MLP(
              (gate_proj): Linear(in_features=16, out_features=64, bias=False)
              (up_proj): Linear(in_features=16, out_features=64, bias=False)
              (down_proj): Linear(in_features=64, out_features=16, bias=False)
              (act_fn): GELUTanh()
            )
            (input_layernorm): DiffusionGemmaRMSNorm()
            (post_attention_layernorm): DiffusionGemmaRMSNorm()
            (pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
            (post_feedforward_layernorm): DiffusionGemmaRMSNorm()
            (router): DiffusionGemmaTextRouter(
              (norm): DiffusionGemmaRMSNorm()
              (proj): Linear(in_features=16, out_features=32, bias=False)
            )
            (experts): DiffusionGemmaTextExperts(
              (act_fn): GELUTanh()
            )
            (post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
            (post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
            (pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
          )
          (5): DiffusionGemmaEncoderTextLayer(
            (self_attn): DiffusionGemmaEncoderTextAttention(
              (q_proj): Linear(in_features=16, out_features=64, bias=False)
              (k_proj): Linear(in_features=16, out_features=64, bias=False)
              (o_proj): Linear(in_features=64, out_features=16, bias=False)
              (q_norm): DiffusionGemmaRMSNorm()
              (k_norm): DiffusionGemmaRMSNorm()
              (v_norm): DiffusionGemmaRMSNorm()
            )
            (mlp): DiffusionGemmaText4MLP(
              (gate_proj): Linear(in_features=16, out_features=64, bias=False)
              (up_proj): Linear(in_features=16, out_features=64, bias=False)
              (down_proj): Linear(in_features=64, out_features=16, bias=False)
              (act_fn): GELUTanh()
            )
            (input_layernorm): DiffusionGemmaRMSNorm()
            (post_attention_layernorm): DiffusionGemmaRMSNorm()
            (pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
            (post_feedforward_layernorm): DiffusionGemmaRMSNorm()
            (router): DiffusionGemmaTextRouter(
              (norm): DiffusionGemmaRMSNorm()
              (proj): Linear(in_features=16, out_features=32, bias=False)
            )
            (experts): DiffusionGemmaTextExperts(
              (act_fn): GELUTanh()
            )
            (post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
            (post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
            (pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
          )
          (6-10): 5 x DiffusionGemmaEncoderTextLayer(
            (self_attn): DiffusionGemmaEncoderTextAttention(
              (q_proj): Linear(in_features=16, out_features=32, bias=False)
              (k_proj): Linear(in_features=16, out_features=32, bias=False)
              (v_proj): Linear(in_features=16, out_features=32, bias=False)
              (o_proj): Linear(in_features=32, out_features=16, bias=False)
              (q_norm): DiffusionGemmaRMSNorm()
              (k_norm): DiffusionGemmaRMSNorm()
              (v_norm): DiffusionGemmaRMSNorm()
            )
            (mlp): DiffusionGemmaText4MLP(
              (gate_proj): Linear(in_features=16, out_features=64, bias=False)
              (up_proj): Linear(in_features=16, out_features=64, bias=False)
              (down_proj): Linear(in_features=64, out_features=16, bias=False)
              (act_fn): GELUTanh()
            )
            (input_layernorm): DiffusionGemmaRMSNorm()
            (post_attention_layernorm): DiffusionGemmaRMSNorm()
            (pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
            (post_feedforward_layernorm): DiffusionGemmaRMSNorm()
            (router): DiffusionGemmaTextRouter(
              (norm): DiffusionGemmaRMSNorm()
              (proj): Linear(in_features=16, out_features=32, bias=False)
            )
            (experts): DiffusionGemmaTextExperts(
              (act_fn): GELUTanh()
            )
            (post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
            (post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
            (pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
          )
          (11): DiffusionGemmaEncoderTextLayer(
            (self_attn): DiffusionGemmaEncoderTextAttention(
              (q_proj): Linear(in_features=16, out_features=64, bias=False)
              (k_proj): Linear(in_features=16, out_features=64, bias=False)
              (o_proj): Linear(in_features=64, out_features=16, bias=False)
              (q_norm): DiffusionGemmaRMSNorm()
              (k_norm): DiffusionGemmaRMSNorm()
              (v_norm): DiffusionGemmaRMSNorm()
            )
            (mlp): DiffusionGemmaText4MLP(
              (gate_proj): Linear(in_features=16, out_features=64, bias=False)
              (up_proj): Linear(in_features=16, out_features=64, bias=False)
              (down_proj): Linear(in_features=64, out_features=16, bias=False)
              (act_fn): GELUTanh()
            )
            (input_layernorm): DiffusionGemmaRMSNorm()
            (post_attention_layernorm): DiffusionGemmaRMSNorm()
            (pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
            (post_feedforward_layernorm): DiffusionGemmaRMSNorm()
            (router): DiffusionGemmaTextRouter(
              (norm): DiffusionGemmaRMSNorm()
              (proj): Linear(in_features=16, out_features=32, bias=False)
            )
            (experts): DiffusionGemmaTextExperts(
              (act_fn): GELUTanh()
            )
            (post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
            (post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
            (pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
          )
        )
        (norm): DiffusionGemmaRMSNorm()
        (rotary_emb): DiffusionGemmaTextRotaryEmbedding()
      )
      (vision_tower): Gemma4VisionModel(
        (patch_embedder): Gemma4VisionPatchEmbedder(
          (input_proj): Linear(in_features=768, out_features=64, bias=False)
        )
        (encoder): Gemma4VisionEncoder(
          (rotary_emb): Gemma4VisionRotaryEmbedding()
          (layers): ModuleList(
            (0-1): 2 x Gemma4VisionEncoderLayer(
              (self_attn): Gemma4VisionAttention(
                (q_proj): Gemma4ClippableLinear(
                  (linear): Linear(in_features=64, out_features=64, bias=False)
                )
                (k_proj): Gemma4ClippableLinear(
                  (linear): Linear(in_features=64, out_features=64, bias=False)
                )
                (v_proj): Gemma4ClippableLinear(
                  (linear): Linear(in_features=64, out_features=64, bias=False)
                )
                (o_proj): Gemma4ClippableLinear(
                  (linear): Linear(in_features=64, out_features=64, bias=False)
                )
                (q_norm): Gemma4RMSNorm()
                (k_norm): Gemma4RMSNorm()
                (v_norm): Gemma4RMSNorm()
              )
              (mlp): Gemma4VisionMLP(
                (gate_proj): Gemma4ClippableLinear(
                  (linear): Linear(in_features=64, out_features=128, bias=False)
                )
                (up_proj): Gemma4ClippableLinear(
                  (linear): Linear(in_features=64, out_features=128, bias=False)
                )
                (down_proj): Gemma4ClippableLinear(
                  (linear): Linear(in_features=128, out_features=64, bias=False)
                )
                (act_fn): GELUTanh()
              )
              (input_layernorm): Gemma4RMSNorm()
              (post_attention_layernorm): Gemma4RMSNorm()
              (pre_feedforward_layernorm): Gemma4RMSNorm()
              (post_feedforward_layernorm): Gemma4RMSNorm()
            )
          )
        )
        (pooler): Gemma4VisionPooler()
      )
      (embed_vision): DiffusionGemmaMultimodalEmbedder(
        (embedding_projection): Linear(in_features=64, out_features=16, bias=False)
        (embedding_pre_projection_norm): DiffusionGemmaRMSNorm()
      )
    )
    (decoder): DiffusionGemmaDecoderModel(
      (embed_tokens): DiffusionGemmaTextScaledWordEmbedding(262144, 16, padding_idx=0)
      (layers): ModuleList(
        (0-4): 5 x DiffusionGemmaDecoderTextLayer(
          (self_attn): DiffusionGemmaDecoderTextAttention(
            (q_proj): Linear(in_features=16, out_features=32, bias=False)
            (k_proj): Linear(in_features=16, out_features=32, bias=False)
            (v_proj): Linear(in_features=16, out_features=32, bias=False)
            (o_proj): Linear(in_features=32, out_features=16, bias=False)
            (q_norm): DiffusionGemmaRMSNorm()
            (k_norm): DiffusionGemmaRMSNorm()
            (v_norm): DiffusionGemmaRMSNorm()
          )
          (mlp): DiffusionGemmaText4MLP(
            (gate_proj): Linear(in_features=16, out_features=64, bias=False)
            (up_proj): Linear(in_features=16, out_features=64, bias=False)
            (down_proj): Linear(in_features=64, out_features=16, bias=False)
            (act_fn): GELUTanh()
          )
          (input_layernorm): DiffusionGemmaRMSNorm()
          (post_attention_layernorm): DiffusionGemmaRMSNorm()
          (pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
          (post_feedforward_layernorm): DiffusionGemmaRMSNorm()
          (router): DiffusionGemmaTextRouter(
            (norm): DiffusionGemmaRMSNorm()
            (proj): Linear(in_features=16, out_features=32, bias=False)
          )
          (experts): DiffusionGemmaTextExperts(
            (act_fn): GELUTanh()
          )
          (post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
          (post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
          (pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
        )
        (5): DiffusionGemmaDecoderTextLayer(
          (self_attn): DiffusionGemmaDecoderTextAttention(
            (q_proj): Linear(in_features=16, out_features=64, bias=False)
            (k_proj): Linear(in_features=16, out_features=64, bias=False)
            (o_proj): Linear(in_features=64, out_features=16, bias=False)
            (q_norm): DiffusionGemmaRMSNorm()
            (k_norm): DiffusionGemmaRMSNorm()
            (v_norm): DiffusionGemmaRMSNorm()
          )
          (mlp): DiffusionGemmaText4MLP(
            (gate_proj): Linear(in_features=16, out_features=64, bias=False)
            (up_proj): Linear(in_features=16, out_features=64, bias=False)
            (down_proj): Linear(in_features=64, out_features=16, bias=False)
            (act_fn): GELUTanh()
          )
          (input_layernorm): DiffusionGemmaRMSNorm()
          (post_attention_layernorm): DiffusionGemmaRMSNorm()
          (pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
          (post_feedforward_layernorm): DiffusionGemmaRMSNorm()
          (router): DiffusionGemmaTextRouter(
            (norm): DiffusionGemmaRMSNorm()
            (proj): Linear(in_features=16, out_features=32, bias=False)
          )
          (experts): DiffusionGemmaTextExperts(
            (act_fn): GELUTanh()
          )
          (post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
          (post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
          (pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
        )
        (6-10): 5 x DiffusionGemmaDecoderTextLayer(
          (self_attn): DiffusionGemmaDecoderTextAttention(
            (q_proj): Linear(in_features=16, out_features=32, bias=False)
            (k_proj): Linear(in_features=16, out_features=32, bias=False)
            (v_proj): Linear(in_features=16, out_features=32, bias=False)
            (o_proj): Linear(in_features=32, out_features=16, bias=False)
            (q_norm): DiffusionGemmaRMSNorm()
            (k_norm): DiffusionGemmaRMSNorm()
            (v_norm): DiffusionGemmaRMSNorm()
          )
          (mlp): DiffusionGemmaText4MLP(
            (gate_proj): Linear(in_features=16, out_features=64, bias=False)
            (up_proj): Linear(in_features=16, out_features=64, bias=False)
            (down_proj): Linear(in_features=64, out_features=16, bias=False)
            (act_fn): GELUTanh()
          )
          (input_layernorm): DiffusionGemmaRMSNorm()
          (post_attention_layernorm): DiffusionGemmaRMSNorm()
          (pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
          (post_feedforward_layernorm): DiffusionGemmaRMSNorm()
          (router): DiffusionGemmaTextRouter(
            (norm): DiffusionGemmaRMSNorm()
            (proj): Linear(in_features=16, out_features=32, bias=False)
          )
          (experts): DiffusionGemmaTextExperts(
            (act_fn): GELUTanh()
          )
          (post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
          (post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
          (pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
        )
        (11): DiffusionGemmaDecoderTextLayer(
          (self_attn): DiffusionGemmaDecoderTextAttention(
            (q_proj): Linear(in_features=16, out_features=64, bias=False)
            (k_proj): Linear(in_features=16, out_features=64, bias=False)
            (o_proj): Linear(in_features=64, out_features=16, bias=False)
            (q_norm): DiffusionGemmaRMSNorm()
            (k_norm): DiffusionGemmaRMSNorm()
            (v_norm): DiffusionGemmaRMSNorm()
          )
          (mlp): DiffusionGemmaText4MLP(
            (gate_proj): Linear(in_features=16, out_features=64, bias=False)
            (up_proj): Linear(in_features=16, out_features=64, bias=False)
            (down_proj): Linear(in_features=64, out_features=16, bias=False)
            (act_fn): GELUTanh()
          )
          (input_layernorm): DiffusionGemmaRMSNorm()
          (post_attention_layernorm): DiffusionGemmaRMSNorm()
          (pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
          (post_feedforward_layernorm): DiffusionGemmaRMSNorm()
          (router): DiffusionGemmaTextRouter(
            (norm): DiffusionGemmaRMSNorm()
            (proj): Linear(in_features=16, out_features=32, bias=False)
          )
          (experts): DiffusionGemmaTextExperts(
            (act_fn): GELUTanh()
          )
          (post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
          (post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
          (pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
        )
      )
      (norm): DiffusionGemmaRMSNorm()
      (rotary_emb): DiffusionGemmaTextRotaryEmbedding()
      (self_conditioning): DiffusionGemmaSelfConditioning(
        (pre_norm): DiffusionGemmaRMSNorm()
        (post_norm): DiffusionGemmaRMSNorm()
        (gate_proj): Linear(in_features=16, out_features=64, bias=False)
        (up_proj): Linear(in_features=16, out_features=64, bias=False)
        (down_proj): Linear(in_features=64, out_features=16, bias=False)
        (act_fn): GELUTanh()
      )
    )
  )
  (lm_head): Linear(in_features=16, out_features=262144, bias=False)
)
```

</details>

### Test environment:

- Pillow: 13.0.0
- huggingface_hub: 2.3.0
- numpy: 2.3.5
- safetensors: 0.8.0
- tokenizers: 0.23.3
- torch: 2.13.0
- transformers: 5.19.0
### Change log:
- 2026-10-23: Initial version.
This repo is generated by GPT-6.1-Sol

	---
	library_name: transformers
	base_model:
	- google/diffusiongemma-26B-A4B-it
	---

	This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [google/diffusiongemma-26B-A4B-it](https://huggingface.co/google/diffusiongemma-26B-A4B-it).

	Structural comparison with `google/diffusiongemma-26B-A4B-it`:

	\| Feature \| Source \| Tiny \|
	\|---\|---:\|---:\|
	\| Input modalities \| text, image, video \| same \|
	\| Vocabulary / tied embeddings \| 262,144 / yes \| same \|
	\| Text layers \| 30 \| 12; two 5-sliding + 1-full cycles \|
	\| Text width / local head dimension \| 2,816 / 256 \| 16 / 32 \|
	\| Full-attention head dimension \| 512 \| 64 \|
	\| MoE experts / active experts \| 128 / 8 \| 32 / 8 \|
	\| Vision layers / width \| 27 / 1,152 \| 2 / 64 \|
	\| Canvas length and self-conditioning \| 256 / present \| same \|
	\| Stored precision \| BF16 \| BF16 \|

	The encoder/decoder weight sharing and the decoder self-conditioning branch are
	provided by the native `DiffusionGemmaForBlockDiffusion` implementation rather
	than serialized as independent copies.

	\| File path \| Size \|
	\|------\|------\|
	\| model.safetensors \| 12.6MB \|


	### Example usage:

	- Transformers (✅ verified)

	```python
	import numpy as np
	import torch
	from PIL import Image
	from transformers import AutoProcessor, DiffusionGemmaForBlockDiffusion
	from transformers.video_utils import VideoMetadata

	model_id = "tiny-random/diffusiongemma-moe"
	device = "cuda" if torch.cuda.is_available() else "cpu"
	dtype = torch.bfloat16 if device == "cuda" else torch.float32
	model = DiffusionGemmaForBlockDiffusion.from_pretrained(model_id, dtype=dtype).to(device)
	processor = AutoProcessor.from_pretrained(model_id)
	image = Image.new("RGB", (64, 64), "red")
	video = np.stack([np.asarray(Image.new("RGB", (64, 64), color)) for color in ("red", "green", "blue", "yellow")])
	messages = [{"role": "user", "content": [
	{"type": "image", "image": image},
	{"type": "video", "video": video},
	{"type": "text", "text": "Describe the image and video."},
	]}]
	inputs = processor.apply_chat_template(
	messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt",
	do_sample_frames=False,
	video_metadata=[VideoMetadata(total_num_frames=4, fps=2, frames_indices=[0, 1, 2, 3])],
	).to(device)
	output = model.generate(**inputs, max_new_tokens=10, max_denoising_steps=2)
	print(processor.decode(output.sequences[0], skip_special_tokens=True)[-500:])
	```

	### Codes to create this repo (✅ verified):

	<details><summary>Click to expand</summary>

	```python
	import json
	from pathlib import Path
	from shutil import copyfile

	import torch
	from huggingface_hub import hf_hub_download, list_repo_files
	from transformers import AutoConfig, DiffusionGemmaForBlockDiffusion, set_seed

	source_model_id = "google/diffusiongemma-26B-A4B-it"
	save_folder = "/tmp/tiny-random/diffusiongemma-moe"
	source_revision = "f7f5b7f5fa82ffc52addd066915886d497f5517b"
	set_seed(42)
	folder = Path(save_folder)
	folder.mkdir(parents=True, exist_ok=True)
	raw = json.loads(Path(hf_hub_download(source_model_id, "config.json", revision=source_revision)).read_text())
	text = raw["text_config"]
	text.update(
	hidden_size=16, head_dim=32, num_attention_heads=1, num_key_value_heads=1,
	intermediate_size=64, moe_intermediate_size=32, num_experts=32, top_k_experts=8,
	num_hidden_layers=12,
	layer_types=["sliding_attention"] * 5 + ["full_attention"] + ["sliding_attention"] * 5 + ["full_attention"],
	per_layer_config={"5": {"head_dim": 64, "num_key_value_heads": 1}, "11": {"head_dim": 64, "num_key_value_heads": 1}},
	)
	raw["vision_config"].update(
	hidden_size=64, intermediate_size=128, num_hidden_layers=2,
	num_attention_heads=2, num_key_value_heads=2, head_dim=32,
	)
	(folder / "config.json").write_text(json.dumps(raw, indent=2), encoding="utf-8")
	config = AutoConfig.from_pretrained(folder)
	model = DiffusionGemmaForBlockDiffusion(config).to(torch.bfloat16)
	with torch.no_grad():
	for name, parameter in sorted(model.named_parameters()):
	if not parameter.is_floating_point():
	continue
	if name.endswith("norm.weight"):
	parameter.fill_(1)
	else:
	torch.nn.init.normal_(parameter, mean=0, std=0.02)
	model.save_pretrained(folder, safe_serialization=True)
	assets = {"chat_template.jinja", "generation_config.json", "model_index.json", "processor_config.json", "scheduler/scheduler_config.json", "tokenizer.json", "tokenizer_config.json"}
	for filename in sorted(set(list_repo_files(source_model_id, revision=source_revision)) & assets):
	destination = folder / filename
	destination.parent.mkdir(parents=True, exist_ok=True)
	copyfile(hf_hub_download(source_model_id, filename, revision=source_revision), destination)
	```

	</details>

	### Printing the model:

	<details><summary>Click to expand</summary>

	```text
	DiffusionGemmaForBlockDiffusion(
	(model): DiffusionGemmaModel(
	(encoder): DiffusionGemmaEncoderModel(
	(language_model): DiffusionGemmaEncoderTextModel(
	(embed_tokens): DiffusionGemmaTextScaledWordEmbedding(262144, 16, padding_idx=0)
	(layers): ModuleList(
	(0-4): 5 x DiffusionGemmaEncoderTextLayer(
	(self_attn): DiffusionGemmaEncoderTextAttention(
	(q_proj): Linear(in_features=16, out_features=32, bias=False)
	(k_proj): Linear(in_features=16, out_features=32, bias=False)
	(v_proj): Linear(in_features=16, out_features=32, bias=False)
	(o_proj): Linear(in_features=32, out_features=16, bias=False)
	(q_norm): DiffusionGemmaRMSNorm()
	(k_norm): DiffusionGemmaRMSNorm()
	(v_norm): DiffusionGemmaRMSNorm()
	)
	(mlp): DiffusionGemmaText4MLP(
	(gate_proj): Linear(in_features=16, out_features=64, bias=False)
	(up_proj): Linear(in_features=16, out_features=64, bias=False)
	(down_proj): Linear(in_features=64, out_features=16, bias=False)
	(act_fn): GELUTanh()
	)
	(input_layernorm): DiffusionGemmaRMSNorm()
	(post_attention_layernorm): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(router): DiffusionGemmaTextRouter(
	(norm): DiffusionGemmaRMSNorm()
	(proj): Linear(in_features=16, out_features=32, bias=False)
	)
	(experts): DiffusionGemmaTextExperts(
	(act_fn): GELUTanh()
	)
	(post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	)
	(5): DiffusionGemmaEncoderTextLayer(
	(self_attn): DiffusionGemmaEncoderTextAttention(
	(q_proj): Linear(in_features=16, out_features=64, bias=False)
	(k_proj): Linear(in_features=16, out_features=64, bias=False)
	(o_proj): Linear(in_features=64, out_features=16, bias=False)
	(q_norm): DiffusionGemmaRMSNorm()
	(k_norm): DiffusionGemmaRMSNorm()
	(v_norm): DiffusionGemmaRMSNorm()
	)
	(mlp): DiffusionGemmaText4MLP(
	(gate_proj): Linear(in_features=16, out_features=64, bias=False)
	(up_proj): Linear(in_features=16, out_features=64, bias=False)
	(down_proj): Linear(in_features=64, out_features=16, bias=False)
	(act_fn): GELUTanh()
	)
	(input_layernorm): DiffusionGemmaRMSNorm()
	(post_attention_layernorm): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(router): DiffusionGemmaTextRouter(
	(norm): DiffusionGemmaRMSNorm()
	(proj): Linear(in_features=16, out_features=32, bias=False)
	)
	(experts): DiffusionGemmaTextExperts(
	(act_fn): GELUTanh()
	)
	(post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	)
	(6-10): 5 x DiffusionGemmaEncoderTextLayer(
	(self_attn): DiffusionGemmaEncoderTextAttention(
	(q_proj): Linear(in_features=16, out_features=32, bias=False)
	(k_proj): Linear(in_features=16, out_features=32, bias=False)
	(v_proj): Linear(in_features=16, out_features=32, bias=False)
	(o_proj): Linear(in_features=32, out_features=16, bias=False)
	(q_norm): DiffusionGemmaRMSNorm()
	(k_norm): DiffusionGemmaRMSNorm()
	(v_norm): DiffusionGemmaRMSNorm()
	)
	(mlp): DiffusionGemmaText4MLP(
	(gate_proj): Linear(in_features=16, out_features=64, bias=False)
	(up_proj): Linear(in_features=16, out_features=64, bias=False)
	(down_proj): Linear(in_features=64, out_features=16, bias=False)
	(act_fn): GELUTanh()
	)
	(input_layernorm): DiffusionGemmaRMSNorm()
	(post_attention_layernorm): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(router): DiffusionGemmaTextRouter(
	(norm): DiffusionGemmaRMSNorm()
	(proj): Linear(in_features=16, out_features=32, bias=False)
	)
	(experts): DiffusionGemmaTextExperts(
	(act_fn): GELUTanh()
	)
	(post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	)
	(11): DiffusionGemmaEncoderTextLayer(
	(self_attn): DiffusionGemmaEncoderTextAttention(
	(q_proj): Linear(in_features=16, out_features=64, bias=False)
	(k_proj): Linear(in_features=16, out_features=64, bias=False)
	(o_proj): Linear(in_features=64, out_features=16, bias=False)
	(q_norm): DiffusionGemmaRMSNorm()
	(k_norm): DiffusionGemmaRMSNorm()
	(v_norm): DiffusionGemmaRMSNorm()
	)
	(mlp): DiffusionGemmaText4MLP(
	(gate_proj): Linear(in_features=16, out_features=64, bias=False)
	(up_proj): Linear(in_features=16, out_features=64, bias=False)
	(down_proj): Linear(in_features=64, out_features=16, bias=False)
	(act_fn): GELUTanh()
	)
	(input_layernorm): DiffusionGemmaRMSNorm()
	(post_attention_layernorm): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(router): DiffusionGemmaTextRouter(
	(norm): DiffusionGemmaRMSNorm()
	(proj): Linear(in_features=16, out_features=32, bias=False)
	)
	(experts): DiffusionGemmaTextExperts(
	(act_fn): GELUTanh()
	)
	(post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	)
	)
	(norm): DiffusionGemmaRMSNorm()
	(rotary_emb): DiffusionGemmaTextRotaryEmbedding()
	)
	(vision_tower): Gemma4VisionModel(
	(patch_embedder): Gemma4VisionPatchEmbedder(
	(input_proj): Linear(in_features=768, out_features=64, bias=False)
	)
	(encoder): Gemma4VisionEncoder(
	(rotary_emb): Gemma4VisionRotaryEmbedding()
	(layers): ModuleList(
	(0-1): 2 x Gemma4VisionEncoderLayer(
	(self_attn): Gemma4VisionAttention(
	(q_proj): Gemma4ClippableLinear(
	(linear): Linear(in_features=64, out_features=64, bias=False)
	)
	(k_proj): Gemma4ClippableLinear(
	(linear): Linear(in_features=64, out_features=64, bias=False)
	)
	(v_proj): Gemma4ClippableLinear(
	(linear): Linear(in_features=64, out_features=64, bias=False)
	)
	(o_proj): Gemma4ClippableLinear(
	(linear): Linear(in_features=64, out_features=64, bias=False)
	)
	(q_norm): Gemma4RMSNorm()
	(k_norm): Gemma4RMSNorm()
	(v_norm): Gemma4RMSNorm()
	)
	(mlp): Gemma4VisionMLP(
	(gate_proj): Gemma4ClippableLinear(
	(linear): Linear(in_features=64, out_features=128, bias=False)
	)
	(up_proj): Gemma4ClippableLinear(
	(linear): Linear(in_features=64, out_features=128, bias=False)
	)
	(down_proj): Gemma4ClippableLinear(
	(linear): Linear(in_features=128, out_features=64, bias=False)
	)
	(act_fn): GELUTanh()
	)
	(input_layernorm): Gemma4RMSNorm()
	(post_attention_layernorm): Gemma4RMSNorm()
	(pre_feedforward_layernorm): Gemma4RMSNorm()
	(post_feedforward_layernorm): Gemma4RMSNorm()
	)
	)
	)
	(pooler): Gemma4VisionPooler()
	)
	(embed_vision): DiffusionGemmaMultimodalEmbedder(
	(embedding_projection): Linear(in_features=64, out_features=16, bias=False)
	(embedding_pre_projection_norm): DiffusionGemmaRMSNorm()
	)
	)
	(decoder): DiffusionGemmaDecoderModel(
	(embed_tokens): DiffusionGemmaTextScaledWordEmbedding(262144, 16, padding_idx=0)
	(layers): ModuleList(
	(0-4): 5 x DiffusionGemmaDecoderTextLayer(
	(self_attn): DiffusionGemmaDecoderTextAttention(
	(q_proj): Linear(in_features=16, out_features=32, bias=False)
	(k_proj): Linear(in_features=16, out_features=32, bias=False)
	(v_proj): Linear(in_features=16, out_features=32, bias=False)
	(o_proj): Linear(in_features=32, out_features=16, bias=False)
	(q_norm): DiffusionGemmaRMSNorm()
	(k_norm): DiffusionGemmaRMSNorm()
	(v_norm): DiffusionGemmaRMSNorm()
	)
	(mlp): DiffusionGemmaText4MLP(
	(gate_proj): Linear(in_features=16, out_features=64, bias=False)
	(up_proj): Linear(in_features=16, out_features=64, bias=False)
	(down_proj): Linear(in_features=64, out_features=16, bias=False)
	(act_fn): GELUTanh()
	)
	(input_layernorm): DiffusionGemmaRMSNorm()
	(post_attention_layernorm): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(router): DiffusionGemmaTextRouter(
	(norm): DiffusionGemmaRMSNorm()
	(proj): Linear(in_features=16, out_features=32, bias=False)
	)
	(experts): DiffusionGemmaTextExperts(
	(act_fn): GELUTanh()
	)
	(post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	)
	(5): DiffusionGemmaDecoderTextLayer(
	(self_attn): DiffusionGemmaDecoderTextAttention(
	(q_proj): Linear(in_features=16, out_features=64, bias=False)
	(k_proj): Linear(in_features=16, out_features=64, bias=False)
	(o_proj): Linear(in_features=64, out_features=16, bias=False)
	(q_norm): DiffusionGemmaRMSNorm()
	(k_norm): DiffusionGemmaRMSNorm()
	(v_norm): DiffusionGemmaRMSNorm()
	)
	(mlp): DiffusionGemmaText4MLP(
	(gate_proj): Linear(in_features=16, out_features=64, bias=False)
	(up_proj): Linear(in_features=16, out_features=64, bias=False)
	(down_proj): Linear(in_features=64, out_features=16, bias=False)
	(act_fn): GELUTanh()
	)
	(input_layernorm): DiffusionGemmaRMSNorm()
	(post_attention_layernorm): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(router): DiffusionGemmaTextRouter(
	(norm): DiffusionGemmaRMSNorm()
	(proj): Linear(in_features=16, out_features=32, bias=False)
	)
	(experts): DiffusionGemmaTextExperts(
	(act_fn): GELUTanh()
	)
	(post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	)
	(6-10): 5 x DiffusionGemmaDecoderTextLayer(
	(self_attn): DiffusionGemmaDecoderTextAttention(
	(q_proj): Linear(in_features=16, out_features=32, bias=False)
	(k_proj): Linear(in_features=16, out_features=32, bias=False)
	(v_proj): Linear(in_features=16, out_features=32, bias=False)
	(o_proj): Linear(in_features=32, out_features=16, bias=False)
	(q_norm): DiffusionGemmaRMSNorm()
	(k_norm): DiffusionGemmaRMSNorm()
	(v_norm): DiffusionGemmaRMSNorm()
	)
	(mlp): DiffusionGemmaText4MLP(
	(gate_proj): Linear(in_features=16, out_features=64, bias=False)
	(up_proj): Linear(in_features=16, out_features=64, bias=False)
	(down_proj): Linear(in_features=64, out_features=16, bias=False)
	(act_fn): GELUTanh()
	)
	(input_layernorm): DiffusionGemmaRMSNorm()
	(post_attention_layernorm): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(router): DiffusionGemmaTextRouter(
	(norm): DiffusionGemmaRMSNorm()
	(proj): Linear(in_features=16, out_features=32, bias=False)
	)
	(experts): DiffusionGemmaTextExperts(
	(act_fn): GELUTanh()
	)
	(post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	)
	(11): DiffusionGemmaDecoderTextLayer(
	(self_attn): DiffusionGemmaDecoderTextAttention(
	(q_proj): Linear(in_features=16, out_features=64, bias=False)
	(k_proj): Linear(in_features=16, out_features=64, bias=False)
	(o_proj): Linear(in_features=64, out_features=16, bias=False)
	(q_norm): DiffusionGemmaRMSNorm()
	(k_norm): DiffusionGemmaRMSNorm()
	(v_norm): DiffusionGemmaRMSNorm()
	)
	(mlp): DiffusionGemmaText4MLP(
	(gate_proj): Linear(in_features=16, out_features=64, bias=False)
	(up_proj): Linear(in_features=16, out_features=64, bias=False)
	(down_proj): Linear(in_features=64, out_features=16, bias=False)
	(act_fn): GELUTanh()
	)
	(input_layernorm): DiffusionGemmaRMSNorm()
	(post_attention_layernorm): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm): DiffusionGemmaRMSNorm()
	(router): DiffusionGemmaTextRouter(
	(norm): DiffusionGemmaRMSNorm()
	(proj): Linear(in_features=16, out_features=32, bias=False)
	)
	(experts): DiffusionGemmaTextExperts(
	(act_fn): GELUTanh()
	)
	(post_feedforward_layernorm_1): DiffusionGemmaRMSNorm()
	(post_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	(pre_feedforward_layernorm_2): DiffusionGemmaRMSNorm()
	)
	)
	(norm): DiffusionGemmaRMSNorm()
	(rotary_emb): DiffusionGemmaTextRotaryEmbedding()
	(self_conditioning): DiffusionGemmaSelfConditioning(
	(pre_norm): DiffusionGemmaRMSNorm()
	(post_norm): DiffusionGemmaRMSNorm()
	(gate_proj): Linear(in_features=16, out_features=64, bias=False)
	(up_proj): Linear(in_features=16, out_features=64, bias=False)
	(down_proj): Linear(in_features=64, out_features=16, bias=False)
	(act_fn): GELUTanh()
	)
	)
	)
	(lm_head): Linear(in_features=16, out_features=262144, bias=False)
	)
	```

	</details>

	### Test environment:

	- Pillow: 13.0.0
	- huggingface_hub: 2.3.0
	- numpy: 2.3.5
	- safetensors: 0.8.0
	- tokenizers: 0.23.3
	- torch: 2.13.0
	- transformers: 5.19.0

	### Change log:

	- 2026-10-23: Initial version.

	This repo is generated by GPT-6.1-Sol