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/embeddinggemma-2",
+    "commit_id": "914f7f89142e33e77833254d9c9b90c3cef7303b"
+  },
+  "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"
+  }
+}

1_Pooling/config.json

@@ -0,0 +1,5 @@
+{
+    "embedding_dimension": 768,
+    "pooling_mode": "mean",
+    "include_prompt": true
+}

2_Normalize/config.json

@@ -0,0 +1,4 @@
+{
+    "module_input_name": "sentence_embedding",
+    "module_output_name": "sentence_embedding"
+}

README.md

@@ -0,0 +1,394 @@
+---
+library_name: transformers
+base_model:
+- google/embeddinggemma-2
+---
+
+This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [google/embeddinggemma-2](https://huggingface.co/google/embeddinggemma-2).
+
+Structural comparison with `google/embeddinggemma-2`:
+
+| Feature | Source | Tiny |
+|---|---:|---:|
+| Input modalities | text, image, video, audio | same |
+| Vocabulary rows | 262,144 | same |
+| Output embedding dimension | 768 | same |
+| Text layers | 24 | 12; two 5-sliding + 1-full cycles |
+| Text width / local head dimension | 512 / 256 | 16 / 32 |
+| Full-attention head dimension | 512 | 64 |
+| Vision layers / width | 16 / 768 | 2 / 64 |
+| Audio layers / width | 12 / 1,024 | 2 / 64 |
+| PLE | projection-only | same |
+| Stored precision | BF16 | BF16 |
+
+The output embedding dimension intentionally remains 768; it is a source-model
+interface rather than a vocabulary or hidden-width reduction target.
+
+| File path | Size |
+|------|------|
+| model.safetensors | 12.0MB |
+
+
+### Example usage:
+
+- Transformers (✅ verified)
+
+```python
+import numpy as np
+import torch
+from PIL import Image
+from transformers import AutoProcessor, EmbeddingGemma2Model
+from transformers.video_utils import VideoMetadata
+
+model_id = "tiny-random/embeddinggemma-2"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.bfloat16 if device == "cuda" else torch.float32
+model = EmbeddingGemma2Model.from_pretrained(model_id, dtype=dtype).to(device).eval()
+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")])
+audio = np.zeros(1_600, dtype=np.float32)
+text = f"{processor.image_token} {processor.video_token} {processor.audio_token}"
+inputs = processor(
+    text=[text], images=[[image]], videos=[video], audio=[audio], return_tensors="pt",
+    do_sample_frames=False,
+    video_metadata=[VideoMetadata(total_num_frames=4, fps=2, frames_indices=[0, 1, 2, 3])],
+).to(device)
+with torch.inference_mode():
+    embeddings = model(**inputs).last_hidden_state.mean(dim=1)
+print(embeddings.shape)
+```
+
+### 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, EmbeddingGemma2Model, set_seed
+
+source_model_id = "google/embeddinggemma-2"
+save_folder = "/tmp/tiny-random/embeddinggemma-2"
+source_revision = "914f7f89142e33e77833254d9c9b90c3cef7303b"
+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, hidden_size_per_layer_input=16, head_dim=32,
+    num_attention_heads=1, num_key_value_heads=1, intermediate_size=64,
+    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, global_head_dim=32,
+)
+raw["audio_config"].update(
+    hidden_size=64, num_attention_heads=2, num_hidden_layers=2,
+    # Gemma4Audio flattens frequency bins after two stride-2 convolutions.
+    # Its projection formula requires the first channel count to remain 128
+    # for the source processor's 128-bin mel features.
+    output_proj_dims=64, subsampling_conv_channels=[128, 8],
+)
+(folder / "config.json").write_text(json.dumps(raw, indent=2), encoding="utf-8")
+config = AutoConfig.from_pretrained(folder)
+model = EmbeddingGemma2Model(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 = {"1_Pooling/config.json", "2_Normalize/config.json", "chat_template.jinja", "config_sentence_transformers.json", "modules.json", "preprocessor_config.json", "processor_config.json", "sentence_bert_config.json", "tokenizer.json", "tokenizer.model", "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
+EmbeddingGemma2Model(
+  (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()
+  )
+  (language_model): EmbeddingGemma2TextModel(
+    (embed_tokens): EmbeddingGemma2TextScaledWordEmbedding(262144, 16, padding_idx=0)
+    (layers): ModuleList(
+      (0-4): 5 x EmbeddingGemma2EncoderLayer(
+        (self_attn): EmbeddingGemma2Attention(
+          (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): EmbeddingGemma2RMSNorm()
+          (k_norm): EmbeddingGemma2RMSNorm()
+          (v_norm): EmbeddingGemma2RMSNorm()
+        )
+        (mlp): EmbeddingGemma2MLP(
+          (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): EmbeddingGemma2RMSNorm()
+        (post_attention_layernorm): EmbeddingGemma2RMSNorm()
+        (pre_feedforward_layernorm): EmbeddingGemma2RMSNorm()
+        (post_feedforward_layernorm): EmbeddingGemma2RMSNorm()
+        (ple_block): EmbeddingGemma2TextPLEBlock(
+          (act_fn): GELUTanh()
+          (per_layer_input_gate): Linear(in_features=16, out_features=16, bias=False)
+          (per_layer_projection): Linear(in_features=16, out_features=16, bias=False)
+          (post_per_layer_input_norm): EmbeddingGemma2RMSNorm()
+        )
+      )
+      (5): EmbeddingGemma2EncoderLayer(
+        (self_attn): EmbeddingGemma2Attention(
+          (q_proj): Linear(in_features=16, out_features=64, bias=False)
+          (k_proj): Linear(in_features=16, out_features=64, bias=False)
+          (v_proj): Linear(in_features=16, out_features=64, bias=False)
+          (o_proj): Linear(in_features=64, out_features=16, bias=False)
+          (q_norm): EmbeddingGemma2RMSNorm()
+          (k_norm): EmbeddingGemma2RMSNorm()
+          (v_norm): EmbeddingGemma2RMSNorm()
+        )
+        (mlp): EmbeddingGemma2MLP(
+          (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): EmbeddingGemma2RMSNorm()
+        (post_attention_layernorm): EmbeddingGemma2RMSNorm()
+        (pre_feedforward_layernorm): EmbeddingGemma2RMSNorm()
+        (post_feedforward_layernorm): EmbeddingGemma2RMSNorm()
+        (ple_block): EmbeddingGemma2TextPLEBlock(
+          (act_fn): GELUTanh()
+          (per_layer_input_gate): Linear(in_features=16, out_features=16, bias=False)
+          (per_layer_projection): Linear(in_features=16, out_features=16, bias=False)
+          (post_per_layer_input_norm): EmbeddingGemma2RMSNorm()
+        )
+      )
+      (6-10): 5 x EmbeddingGemma2EncoderLayer(
+        (self_attn): EmbeddingGemma2Attention(
+          (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): EmbeddingGemma2RMSNorm()
+          (k_norm): EmbeddingGemma2RMSNorm()
+          (v_norm): EmbeddingGemma2RMSNorm()
+        )
+        (mlp): EmbeddingGemma2MLP(
+          (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): EmbeddingGemma2RMSNorm()
+        (post_attention_layernorm): EmbeddingGemma2RMSNorm()
+        (pre_feedforward_layernorm): EmbeddingGemma2RMSNorm()
+        (post_feedforward_layernorm): EmbeddingGemma2RMSNorm()
+        (ple_block): EmbeddingGemma2TextPLEBlock(
+          (act_fn): GELUTanh()
+          (per_layer_input_gate): Linear(in_features=16, out_features=16, bias=False)
+          (per_layer_projection): Linear(in_features=16, out_features=16, bias=False)
+          (post_per_layer_input_norm): EmbeddingGemma2RMSNorm()
+        )
+      )
+      (11): EmbeddingGemma2EncoderLayer(
+        (self_attn): EmbeddingGemma2Attention(
+          (q_proj): Linear(in_features=16, out_features=64, bias=False)
+          (k_proj): Linear(in_features=16, out_features=64, bias=False)
+          (v_proj): Linear(in_features=16, out_features=64, bias=False)
+          (o_proj): Linear(in_features=64, out_features=16, bias=False)
+          (q_norm): EmbeddingGemma2RMSNorm()
+          (k_norm): EmbeddingGemma2RMSNorm()
+          (v_norm): EmbeddingGemma2RMSNorm()
+        )
+        (mlp): EmbeddingGemma2MLP(
+          (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): EmbeddingGemma2RMSNorm()
+        (post_attention_layernorm): EmbeddingGemma2RMSNorm()
+        (pre_feedforward_layernorm): EmbeddingGemma2RMSNorm()
+        (post_feedforward_layernorm): EmbeddingGemma2RMSNorm()
+        (ple_block): EmbeddingGemma2TextPLEBlock(
+          (act_fn): GELUTanh()
+          (per_layer_input_gate): Linear(in_features=16, out_features=16, bias=False)
+          (per_layer_projection): Linear(in_features=16, out_features=16, bias=False)
+          (post_per_layer_input_norm): EmbeddingGemma2RMSNorm()
+        )
+      )
+    )
+    (norm): EmbeddingGemma2RMSNorm()
+    (rotary_emb): EmbeddingGemma2RotaryEmbedding()
+    (ple): EmbeddingGemma2TextPLE(
+      (per_layer_model_projection): Linear(in_features=16, out_features=192, bias=False)
+      (per_layer_projection_norm): EmbeddingGemma2RMSNorm()
+    )
+    (embedding_projection): Linear(in_features=16, out_features=768, bias=False)
+  )
+  (audio_tower): Gemma4AudioModel(
+    (subsample_conv_projection): Gemma4AudioSubSampleConvProjection(
+      (layer0): Gemma4AudioSubSampleConvProjectionLayer(
+        (conv): Conv2d(1, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
+        (norm): LayerNorm((128,), eps=1e-06, elementwise_affine=True, bias=False)
+        (act): ReLU()
+      )
+      (layer1): Gemma4AudioSubSampleConvProjectionLayer(
+        (conv): Conv2d(128, 8, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
+        (norm): LayerNorm((8,), eps=1e-06, elementwise_affine=True, bias=False)
+        (act): ReLU()
+      )
+      (input_proj_linear): Linear(in_features=256, out_features=64, bias=False)
+    )
+    (rel_pos_enc): Gemma4AudioRelPositionalEncoding()
+    (layers): ModuleList(
+      (0-1): 2 x Gemma4AudioLayer(
+        (feed_forward1): Gemma4AudioFeedForward(
+          (ffw_layer_1): Gemma4ClippableLinear(
+            (linear): Linear(in_features=64, out_features=256, bias=False)
+          )
+          (ffw_layer_2): Gemma4ClippableLinear(
+            (linear): Linear(in_features=256, out_features=64, bias=False)
+          )
+          (pre_layer_norm): Gemma4RMSNorm()
+          (post_layer_norm): Gemma4RMSNorm()
+          (act_fn): SiLUActivation()
+        )
+        (feed_forward2): Gemma4AudioFeedForward(
+          (ffw_layer_1): Gemma4ClippableLinear(
+            (linear): Linear(in_features=64, out_features=256, bias=False)
+          )
+          (ffw_layer_2): Gemma4ClippableLinear(
+            (linear): Linear(in_features=256, out_features=64, bias=False)
+          )
+          (pre_layer_norm): Gemma4RMSNorm()
+          (post_layer_norm): Gemma4RMSNorm()
+          (act_fn): SiLUActivation()
+        )
+        (self_attn): Gemma4AudioAttention(
+          (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)
+          )
+          (post): Gemma4ClippableLinear(
+            (linear): Linear(in_features=64, out_features=64, bias=False)
+          )
+          (relative_k_proj): Linear(in_features=64, out_features=64, bias=False)
+        )
+        (lconv1d): Gemma4AudioLightConv1d(
+          (linear_start): Gemma4ClippableLinear(
+            (linear): Linear(in_features=64, out_features=128, bias=False)
+          )
+          (linear_end): Gemma4ClippableLinear(
+            (linear): Linear(in_features=64, out_features=64, bias=False)
+          )
+          (depthwise_conv1d): Gemma4AudioCausalConv1d(64, 64, kernel_size=(5,), stride=(1,), groups=64, bias=False)
+          (pre_layer_norm): Gemma4RMSNorm()
+          (conv_norm): Gemma4RMSNorm()
+          (act_fn): SiLUActivation()
+        )
+        (norm_pre_attn): Gemma4RMSNorm()
+        (norm_post_attn): Gemma4RMSNorm()
+        (norm_out): Gemma4RMSNorm()
+      )
+    )
+    (output_proj): Linear(in_features=64, out_features=64, bias=True)
+  )
+  (embed_vision): EmbeddingGemma2MultimodalEmbedder(
+    (embedding_projection): Linear(in_features=64, out_features=16, bias=False)
+    (embedding_pre_projection_norm): EmbeddingGemma2RMSNorm()
+  )
+  (embed_audio): EmbeddingGemma2MultimodalEmbedder(
+    (embedding_projection): Linear(in_features=64, out_features=16, bias=False)
+    (embedding_pre_projection_norm): EmbeddingGemma2RMSNorm()
+  )
+)
+```
+
+</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 @@
+{%- for msg in messages if msg.get('role') == 'system' -%}{%- if msg.get('content') is string -%}{{ msg['content'] }}{%- else -%}{%- for item in msg['content'] if item.get('type') == 'text' -%}{{ item['text'] }}{%- endfor -%}{%- endif -%}{%- endfor -%}{%- for msg in messages if msg.get('role') != 'system' -%}{%- if msg.get('content') is string -%}{{ msg['content'] }}{%- else -%}{%- set existing_text = msg['content'] | selectattr('type', 'equalto', 'text') | map(attribute='text') | join -%}{%- set has_manual_placeholders = ('<|image|>' in existing_text) or ('<|video|>' in existing_text) or ('<|audio|>' in existing_text) -%}{%- for item in msg['content'] -%}{%- if item.get('type') == 'text' -%}{{ item['text'] }}{%- elif not has_manual_placeholders and item.get('type') == 'image' -%}<|image|>{%- elif not has_manual_placeholders and item.get('type') == 'video' -%}<|video|>{%- elif not has_manual_placeholders and item.get('type') == 'audio' -%}<|audio|>{%- endif -%}{%- endfor -%}{%- endif -%}{%- endfor -%}

config.json

@@ -0,0 +1,155 @@
+{
+  "architectures": [
+    "EmbeddingGemma2Model"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 64,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 64,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      8
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "bfloat16",
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "embedding_gemma2",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "embedding_dim": 768,
+    "eos_token_id": 1,
+    "head_dim": 32,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 16,
+    "hidden_size_per_layer_input": 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": "embedding_gemma2_text",
+    "num_attention_heads": 1,
+    "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": {
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "vocab_size": 262144
+  },
+  "transformers_version": "5.19.0",
+  "video_token_id": 258884,
+  "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": 32,
+    "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": false,
+    "use_clipped_linears": false
+  },
+  "vision_soft_tokens_per_image": 280
+}

config_sentence_transformers.json

@@ -0,0 +1,38 @@
+{
+  "__version__": {
+    "pytorch": "2.14.0+cu130",
+    "sentence_transformers": "6.1.0",
+    "transformers": "5.18.0.dev0"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "BitextMining": "task: search result | query: ",
+    "Classification": "task: classification | query: ",
+    "Clustering": "task: clustering | query: ",
+    "CodeRetrieval": "task: code retrieval | query: ",
+    "Document": "title: none | text: ",
+    "FactChecking": "task: fact checking | query: ",
+    "InstructionRetrieval": "task: code retrieval | query: ",
+    "MultilabelClassification": "task: classification | query: ",
+    "PairClassification": "task: sentence similarity | query: ",
+    "QuestionAnswering": "task: question answering | query: ",
+    "Reranking": "task: search result | query: ",
+    "Retrieval": "task: search result | query: ",
+    "Retrieval-document": "title: none | text: ",
+    "Retrieval-query": "task: search result | query: ",
+    "STS": "task: sentence similarity | query: ",
+    "SearchQuery": "task: search result | query: ",
+    "SentenceSimilarity": "task: sentence similarity | query: ",
+    "Summarization": "task: sentence similarity | query: ",
+    "document": "title: none | text: ",
+    "query": "task: search result | query: "
+  },
+  "requirements": {
+    "sentence-transformers": {
+      "reason": "Older versions ignore the order of multimodal dict inputs and cannot put several images or texts into a single embedding.",
+      "specifier": ">=6.1.0"
+    }
+  },
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea7d54f9a3b5ad9241a54b0902fe8db48f5e849202a6b30f2e72757c43dd87e
+size 11957968

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.base.modules.normalize.Normalize"
+  }
+]

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "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
+}

processor_config.json

@@ -0,0 +1,78 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 280,
+  "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": "EmbeddingGemma2Processor",
+  "video_processor": {
+    "add_timestamps": false,
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 1,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_frames": 32,
+    "max_soft_tokens": 140,
+    "overflow_strategy": "uniform",
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "EmbeddingGemma2VideoProcessor"
+  }
+}

sentence_bert_config.json

@@ -0,0 +1,27 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "image": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "audio": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "video": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "message": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state",
+            "format": "structured"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d777ef5bdc1aa36227abdfb77c3e49e7b9c892d16e1b6bda41c393504828be4
+size 32170510

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e594c8a90eb08d8bda498ff4747977dc827ae0c3c56b5c0d41a605a22d02ef03
+size 4689013

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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|>",
+    "video_token": "<|video|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "EmbeddingGemma2Processor",
+  "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>",
+  "video_token": "<|video|>"
+}