Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.meta.json

@@ -0,0 +1,19 @@
+{
+  "source_model": {
+    "name": "google/diffusiongemma-26B-A4B-it",
+    "commit_id": "f7f5b7f5fa82ffc52addd066915886d497f5517b"
+  },
+  "env": {
+    "python": "3.12.13",
+    "packages": {
+      "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"
+    },
+    "cuda": "13.0"
+  }
+}

README.md

@@ -0,0 +1,463 @@
+---
+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

chat_template.jinja

@@ -0,0 +1,387 @@
+{#
+  Template: Google Gemma 4 Canonical Chat Template
+  Author: Google Gemma Engineering Team
+  Published: 2026-07-09
+  Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.
+#}
+{%- macro format_parameters(properties, required, filter_keys=false) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- set add_comma = false -%}
+        {%- if not filter_keys or key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{ key }}:{
+            {%- if value['description'] -%}
+                description:<|"|>{{ value['description'] }}<|"|>
+                {%- set add_comma = true -%}
+            {%- endif -%}
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <|"|>{{- req_item -}}<|"|>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            {%- if value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'OBJECT' -%}
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                    }
+                {%- elif value is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
+                    }
+                {%- endif -%}
+                {%- if value['required'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- set params = tool_data['function']['parameters'] -%}
+    {%- if params -%}
+        ,parameters:{
+        {%- if params['properties'] -%}
+            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+        {%- endif -%}
+        {%- if params['required'] -%}
+            required:[
+            {%- for item in params['required'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is none -%}
+        {{- 'null' -}}
+    {%- elif argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- elif argument is mapping -%}
+        {{- '{' -}}
+        {%- set ns = namespace(found_first=false) -%}
+        {%- for key, value in argument | dictsort -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {%- if escape_keys -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- else -%}
+                {{- key -}}
+            {%- endif -%}
+            :{{- format_argument(value, escape_keys=escape_keys) -}}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- elif argument is sequence -%}
+        {{- '[' -}}
+        {%- for item in argument -%}
+            {{- format_argument(item, escape_keys=escape_keys) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- argument -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+
+{%- macro format_tool_response_block(tool_name, response) -%}
+    {{- '<|tool_response>' -}}
+    {%- if response is mapping -%}
+        {{- 'response:' + tool_name + '{' -}}
+        {%- for key, value in response | dictsort -%}
+            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- else -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
+    {%- endif -%}
+    {{- '<tool_response|>' -}}
+{%- endmacro -%}
+
+{#- ===== SETUP ===== -#}
+{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
+{%- set loop_messages = messages -%}
+{%- set enable_thinking = enable_thinking | default(false) -%}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+{{- bos_token -}}
+{#- Handle System/Tool Definitions Block -#}
+{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
+    {{- '<|turn>system\n' -}}
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking -%}
+        {{- '<|think|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {{- item['text'] | trim + ' '-}}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<|tool>' -}}
+            {{- format_function_declaration(tool) | trim -}}
+            {{- '<tool|>' -}}
+        {%- endfor %}
+        {%- set ns.prev_message_type = 'tool' -%}
+    {%- endif -%}
+    {{- '<turn|>\n' -}}
+{%- endif %}
+
+{#- Pre-scan: find last user message index for reasoning guard -#}
+{%- set ns_turn = namespace(last_user_idx=-1) -%}
+{%- for i in range(loop_messages | length) -%}
+    {%- if loop_messages[i]['role'] == 'user' -%}
+        {%- set ns_turn.last_user_idx = i -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- if message['role'] != 'tool' -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+    {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
+    {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
+    {%- if not continue_same_model_turn -%}
+        {{- '<|turn>' + role + '\n' }}
+        
+    {%- endif -%}
+
+    {#- Render reasoning/reasoning_content as thinking channel -#}
+    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
+    {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
+    {%- if thinking_text and thinking_gate -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- if message.get('tool_calls') -%}
+                {%- for tool_call in message.get('tool_calls') -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is none -%}
+                    {%- else -%}
+                      {{- raise_exception(
+                          "chat_template: tool_calls[].function.arguments must be a "
+                          "JSON object (mapping), not a string. Deserialize arguments "
+                          "before passing to the template."
+                      ) -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- set ns_tr_out = namespace(flag=false) -%}
+            {%- if message.get('tool_responses') -%}
+                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
+                {%- for tool_response in message.get('tool_responses') -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
+                    {%- set ns_tr_out.flag = true -%}
+                    {%- set ns.prev_message_type = 'tool_response' -%}
+                {%- endfor -%}
+            {%- elif message.get('tool_calls') -%}
+                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
+                {%- set ns_tool_scan = namespace(stopped=false) -%}
+                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
+                    {%- if ns_tool_scan.stopped -%}
+                    {%- elif loop_messages[k]['role'] != 'tool' -%}
+                        {%- set ns_tool_scan.stopped = true -%}
+                    {%- else -%}
+                        {%- set follow = loop_messages[k] -%}
+                        {#- Resolve tool_call_id to function name -#}
+                        {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
+                        {%- for tc in message.get('tool_calls') -%}
+                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
+                                {%- set ns_tname.name = tc['function']['name'] -%}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {#- Handle content as string or content-parts array -#}
+                        {%- set tool_body = follow.get('content') -%}
+                        {%- if tool_body is string -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- elif tool_body is sequence and tool_body is not string -%}
+                            {%- set ns_txt = namespace(s='') -%}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') == 'text' -%}
+                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
+                                {%- endif -%}
+                            {%- endfor -%}
+                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') in ['image', 'image_url'] -%}
+                                    {{- '<|image|>' -}}
+                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}
+                                    {{- '<|audio|>' -}}
+                                {%- elif part.get('type') == 'video' -%}
+                                    {{- '<|video|>' -}}
+                                {%- endif -%}
+                            {%- endfor -%}
+                        {%- else -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- endif -%}
+                        {%- set ns_tr_out.flag = true -%}
+                        {%- set ns.prev_message_type = 'tool_response' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+            {%- set captured_content -%}
+            {%- if message.get('content') is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message.get('content') is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item.get('type') == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item.get('type') in ['image', 'image_url'] -%}
+                        {{- '<|image|>' -}}
+                    {%- elif item.get('type') in ['audio', 'input_audio'] -%}
+                        {{- '<|audio|>' -}}
+                    {%- elif item.get('type') == 'video' -%}
+                        {{- '<|video|>' -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {#- Forward-scan: find next non-tool message role for continuation detection -#}
+        {%- set next_nt = namespace(role=None, found=false) -%}
+        {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
+            {%- if not next_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set next_nt.role = loop_messages[j]['role'] -%}
+                    {%- set next_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+
+        {%- set continues_into_next = (
+            role == 'model'
+            and next_nt.role == 'assistant'
+            and (not message.get('tool_calls') or ns_tr_out.flag)
+        ) -%}
+        
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif continues_into_next -%}
+        {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+    {%- endif -%}
+
+    {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
+    {%- set ns.prev_non_tool_role = message['role'] -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
+        {{- '<|channel>thought\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,122 @@
+{
+  "architectures": [
+    "DiffusionGemmaForBlockDiffusion"
+  ],
+  "boi_token_id": 255999,
+  "canvas_length": 256,
+  "dtype": "bfloat16",
+  "eoi_token_id": 258882,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "diffusion_gemma",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "eos_token_id": 1,
+    "final_logit_softcapping": 30.0,
+    "head_dim": 32,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "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"
+    ],
+    "max_position_embeddings": 262144,
+    "model_type": "diffusion_gemma_text",
+    "moe_intermediate_size": 32,
+    "num_attention_heads": 1,
+    "num_experts": 32,
+    "num_hidden_layers": 12,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "per_layer_config": {
+      "05": {
+        "head_dim": 64
+      },
+      "11": {
+        "head_dim": 64
+      }
+    },
+    "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": "5.19.0",
+  "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": 32,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 64,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 128,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "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": "axial"
+    },
+    "standardize": true,
+    "use_clipped_linears": false
+  },
+  "vision_soft_tokens_per_image": 280
+}

generation_config.json

@@ -0,0 +1,19 @@
+{
+  "confidence_threshold": 0.005,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "max_denoising_steps": 48,
+  "max_new_tokens": 256,
+  "pad_token_id": 0,
+  "sampler_config": {
+    "_cls_name": "EntropyBoundSamplerConfig",
+    "entropy_bound": 0.1
+  },
+  "stability_threshold": 1,
+  "t_max": 0.8,
+  "t_min": 0.4,
+  "transformers_version": "5.8.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507f6d696d56aa68638b31200899fa4e138df38e6155301ef743bc41b56c2d33
+size 12642856

model_index.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "DiffusionGemmaPipeline",
+  "_diffusers_version": "0.39.0.dev0",
+  "model": [
+    "transformers",
+    "DiffusionGemmaForBlockDiffusion"
+  ],
+  "processor": [
+    "transformers",
+    "Gemma4Processor"
+  ],
+  "scheduler": [
+    "diffusers",
+    "BlockRefinementScheduler"
+  ]
+}

processor_config.json

@@ -0,0 +1,75 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "Gemma4VideoProcessor"
+  }
+}

scheduler/scheduler_config.json

@@ -0,0 +1,9 @@
+{
+  "_class_name": "BlockRefinementScheduler",
+  "_diffusers_version": "0.39.0.dev0",
+  "block_length": 32,
+  "editing_threshold": null,
+  "minimal_topk": 1,
+  "num_inference_steps": 32,
+  "threshold": 0.95
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

tokenizer_config.json

@@ -0,0 +1,96 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}