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

README.md

@@ -0,0 +1,387 @@
+---
+library_name: transformers
+base_model:
+- google/gemma-4-E4B-it
+---
+
+This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it).
+
+| File path | Size |
+|------|------|
+| model.safetensors | 9.5MB |
+
+
+### Example usage:
+
+```python
+import torch
+
+from transformers import pipeline, AutoProcessor, AutoModelForCausalLM
+
+model_id = "tiny-random/gemma-4e"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    dtype=torch.bfloat16,
+    device_map="auto"
+)
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user",  "content": [
+        {"type": "audio", "audio": "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/Demos/sample-data/journal1.wav"},
+        {"type": "text", "text": "Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three."},
+    ]},
+]
+text = processor.apply_chat_template(
+    messages, 
+    tokenize=False, 
+    add_generation_prompt=True, 
+    enable_thinking=True,
+)
+inputs = processor(text=text, return_tensors="pt").to(model.device)
+input_len = inputs["input_ids"].shape[-1]
+outputs = model.generate(**inputs, max_new_tokens=16)
+response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
+print(processor.parse_response(response))
+```
+
+### Codes to create this repo:
+
+<details>
+<summary>Click to expand</summary>
+
+```python
+import json
+from pathlib import Path
+
+import torch
+
+from huggingface_hub import file_exists, hf_hub_download
+# from timm.models.mobilenetv5 import decode_arch_def
+from transformers import (
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoProcessor,
+    AutoTokenizer,
+    Gemma4ForConditionalGeneration,
+    GenerationConfig,
+    set_seed,
+)
+
+source_model_id = "google/gemma-4-E4B-it"
+save_folder = "/tmp/tiny-random/gemma-4e"
+
+processor = AutoProcessor.from_pretrained(source_model_id)
+processor.save_pretrained(save_folder)
+
+with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
+    config_json = json.load(f)
+
+config_json['audio_config'].update({
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "hidden_size": 64,
+    'output_proj_dims': 32,
+})
+config_json['text_config'].update({
+    "global_head_dim": 64,
+    "head_dim": 32,
+    "hidden_size": 8,
+    "hidden_size_per_layer_input": 2,
+    "intermediate_size": 64,
+    "layer_types": ['sliding_attention', 'full_attention', 'sliding_attention', 'full_attention'],
+    "num_attention_heads": 8,
+    "num_hidden_layers": 4,
+    "num_key_value_heads": 4,
+    "num_kv_shared_layers": 2,
+})
+config_json['vision_config'].update({
+    'num_hidden_layers': 2,
+    'hidden_size': 8,
+    'intermediate_size': 64,
+    'head_dim': 32,
+    'global_head_dim': 32,
+    'num_attention_heads': 4,
+    "num_key_value_heads": 4,
+})
+
+with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
+    json.dump(config_json, f, indent=2)
+
+config = AutoConfig.from_pretrained(
+    save_folder,
+    trust_remote_code=True,
+)
+print(config)
+
+torch.set_default_dtype(torch.bfloat16)
+model = Gemma4ForConditionalGeneration(config)
+torch.set_default_dtype(torch.float32)
+if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
+    model.generation_config = GenerationConfig.from_pretrained(
+        source_model_id, trust_remote_code=True,
+    )
+set_seed(42)
+model = model.cpu()
+all_numels = 0
+for name, p in sorted(model.named_parameters()):
+    all_numels += p.numel()
+with torch.no_grad():
+    for name, p in sorted(model.named_parameters()):
+        torch.nn.init.normal_(p, 0, 0.2)
+        print(name, p.shape, f'{p.numel() / all_numels * 100: .4f}%')
+model.save_pretrained(save_folder)
+```
+
+</details>
+
+### Printing the model:
+
+<details><summary>Click to expand</summary>
+
+```text
+Gemma4ForConditionalGeneration(
+  (model): Gemma4Model(
+    (language_model): Gemma4TextModel(
+      (embed_tokens): Gemma4TextScaledWordEmbedding(262144, 8, padding_idx=0)
+      (layers): ModuleList(
+        (0): Gemma4TextDecoderLayer(
+          (self_attn): Gemma4TextAttention(
+            (q_norm): Gemma4RMSNorm()
+            (k_norm): Gemma4RMSNorm()
+            (v_norm): Gemma4RMSNorm()
+            (k_proj): Linear(in_features=8, out_features=128, bias=False)
+            (q_proj): Linear(in_features=8, out_features=256, bias=False)
+            (v_proj): Linear(in_features=8, out_features=128, bias=False)
+            (o_proj): Linear(in_features=256, out_features=8, bias=False)
+          )
+          (mlp): Gemma4TextMLP(
+            (gate_proj): Linear(in_features=8, out_features=64, bias=False)
+            (up_proj): Linear(in_features=8, out_features=64, bias=False)
+            (down_proj): Linear(in_features=64, out_features=8, bias=False)
+            (act_fn): GELUTanh()
+          )
+          (input_layernorm): Gemma4RMSNorm()
+          (post_attention_layernorm): Gemma4RMSNorm()
+          (pre_feedforward_layernorm): Gemma4RMSNorm()
+          (post_feedforward_layernorm): Gemma4RMSNorm()
+          (act_fn): GELUTanh()
+          (per_layer_input_gate): Linear(in_features=8, out_features=2, bias=False)
+          (per_layer_projection): Linear(in_features=2, out_features=8, bias=False)
+          (post_per_layer_input_norm): Gemma4RMSNorm()
+        )
+        (1): Gemma4TextDecoderLayer(
+          (self_attn): Gemma4TextAttention(
+            (q_norm): Gemma4RMSNorm()
+            (k_norm): Gemma4RMSNorm()
+            (v_norm): Gemma4RMSNorm()
+            (k_proj): Linear(in_features=8, out_features=256, bias=False)
+            (q_proj): Linear(in_features=8, out_features=512, bias=False)
+            (v_proj): Linear(in_features=8, out_features=256, bias=False)
+            (o_proj): Linear(in_features=512, out_features=8, bias=False)
+          )
+          (mlp): Gemma4TextMLP(
+            (gate_proj): Linear(in_features=8, out_features=64, bias=False)
+            (up_proj): Linear(in_features=8, out_features=64, bias=False)
+            (down_proj): Linear(in_features=64, out_features=8, bias=False)
+            (act_fn): GELUTanh()
+          )
+          (input_layernorm): Gemma4RMSNorm()
+          (post_attention_layernorm): Gemma4RMSNorm()
+          (pre_feedforward_layernorm): Gemma4RMSNorm()
+          (post_feedforward_layernorm): Gemma4RMSNorm()
+          (act_fn): GELUTanh()
+          (per_layer_input_gate): Linear(in_features=8, out_features=2, bias=False)
+          (per_layer_projection): Linear(in_features=2, out_features=8, bias=False)
+          (post_per_layer_input_norm): Gemma4RMSNorm()
+        )
+        (2): Gemma4TextDecoderLayer(
+          (self_attn): Gemma4TextAttention(
+            (q_norm): Gemma4RMSNorm()
+            (k_norm): Gemma4RMSNorm()
+            (v_norm): Gemma4RMSNorm()
+            (k_proj): Linear(in_features=8, out_features=128, bias=False)
+            (q_proj): Linear(in_features=8, out_features=256, bias=False)
+            (v_proj): Linear(in_features=8, out_features=128, bias=False)
+            (o_proj): Linear(in_features=256, out_features=8, bias=False)
+          )
+          (mlp): Gemma4TextMLP(
+            (gate_proj): Linear(in_features=8, out_features=64, bias=False)
+            (up_proj): Linear(in_features=8, out_features=64, bias=False)
+            (down_proj): Linear(in_features=64, out_features=8, bias=False)
+            (act_fn): GELUTanh()
+          )
+          (input_layernorm): Gemma4RMSNorm()
+          (post_attention_layernorm): Gemma4RMSNorm()
+          (pre_feedforward_layernorm): Gemma4RMSNorm()
+          (post_feedforward_layernorm): Gemma4RMSNorm()
+          (act_fn): GELUTanh()
+          (per_layer_input_gate): Linear(in_features=8, out_features=2, bias=False)
+          (per_layer_projection): Linear(in_features=2, out_features=8, bias=False)
+          (post_per_layer_input_norm): Gemma4RMSNorm()
+        )
+        (3): Gemma4TextDecoderLayer(
+          (self_attn): Gemma4TextAttention(
+            (q_norm): Gemma4RMSNorm()
+            (k_norm): Gemma4RMSNorm()
+            (v_norm): Gemma4RMSNorm()
+            (k_proj): Linear(in_features=8, out_features=256, bias=False)
+            (q_proj): Linear(in_features=8, out_features=512, bias=False)
+            (v_proj): Linear(in_features=8, out_features=256, bias=False)
+            (o_proj): Linear(in_features=512, out_features=8, bias=False)
+          )
+          (mlp): Gemma4TextMLP(
+            (gate_proj): Linear(in_features=8, out_features=64, bias=False)
+            (up_proj): Linear(in_features=8, out_features=64, bias=False)
+            (down_proj): Linear(in_features=64, out_features=8, bias=False)
+            (act_fn): GELUTanh()
+          )
+          (input_layernorm): Gemma4RMSNorm()
+          (post_attention_layernorm): Gemma4RMSNorm()
+          (pre_feedforward_layernorm): Gemma4RMSNorm()
+          (post_feedforward_layernorm): Gemma4RMSNorm()
+          (act_fn): GELUTanh()
+          (per_layer_input_gate): Linear(in_features=8, out_features=2, bias=False)
+          (per_layer_projection): Linear(in_features=2, out_features=8, bias=False)
+          (post_per_layer_input_norm): Gemma4RMSNorm()
+        )
+      )
+      (norm): Gemma4RMSNorm()
+      (rotary_emb): Gemma4TextRotaryEmbedding()
+      (embed_tokens_per_layer): Gemma4TextScaledWordEmbedding(262144, 8, padding_idx=0)
+      (per_layer_model_projection): Linear(in_features=8, out_features=8, bias=False)
+      (per_layer_projection_norm): Gemma4RMSNorm()
+    )
+    (vision_tower): Gemma4VisionModel(
+      (patch_embedder): Gemma4VisionPatchEmbedder(
+        (input_proj): Linear(in_features=768, out_features=8, bias=False)
+      )
+      (encoder): Gemma4VisionEncoder(
+        (rotary_emb): Gemma4VisionRotaryEmbedding()
+        (layers): ModuleList(
+          (0-1): 2 x Gemma4VisionEncoderLayer(
+            (self_attn): Gemma4VisionAttention(
+              (q_proj): Gemma4ClippableLinear(
+                (linear): Linear(in_features=8, out_features=128, bias=False)
+              )
+              (k_proj): Gemma4ClippableLinear(
+                (linear): Linear(in_features=8, out_features=128, bias=False)
+              )
+              (v_proj): Gemma4ClippableLinear(
+                (linear): Linear(in_features=8, out_features=128, bias=False)
+              )
+              (o_proj): Gemma4ClippableLinear(
+                (linear): Linear(in_features=128, out_features=8, bias=False)
+              )
+              (q_norm): Gemma4RMSNorm()
+              (k_norm): Gemma4RMSNorm()
+              (v_norm): Gemma4RMSNorm()
+            )
+            (mlp): Gemma4VisionMLP(
+              (gate_proj): Gemma4ClippableLinear(
+                (linear): Linear(in_features=8, out_features=64, bias=False)
+              )
+              (up_proj): Gemma4ClippableLinear(
+                (linear): Linear(in_features=8, out_features=64, bias=False)
+              )
+              (down_proj): Gemma4ClippableLinear(
+                (linear): Linear(in_features=64, out_features=8, bias=False)
+              )
+              (act_fn): GELUTanh()
+            )
+            (input_layernorm): Gemma4RMSNorm()
+            (post_attention_layernorm): Gemma4RMSNorm()
+            (pre_feedforward_layernorm): Gemma4RMSNorm()
+            (post_feedforward_layernorm): Gemma4RMSNorm()
+          )
+        )
+      )
+      (pooler): Gemma4VisionPooler()
+    )
+    (embed_vision): Gemma4MultimodalEmbedder(
+      (embedding_projection): Linear(in_features=8, out_features=8, bias=False)
+      (embedding_pre_projection_norm): Gemma4RMSNorm()
+    )
+    (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)
+          (act): ReLU()
+        )
+        (layer1): Gemma4AudioSubSampleConvProjectionLayer(
+          (conv): Conv2d(128, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
+          (norm): LayerNorm((32,), eps=1e-06, elementwise_affine=True)
+          (act): ReLU()
+        )
+        (input_proj_linear): Linear(in_features=1024, 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=32, bias=True)
+    )
+    (embed_audio): Gemma4MultimodalEmbedder(
+      (embedding_projection): Linear(in_features=32, out_features=8, bias=False)
+      (embedding_pre_projection_norm): Gemma4RMSNorm()
+    )
+  )
+  (lm_head): Linear(in_features=8, out_features=262144, bias=False)
+)
+```
+
+</details>

chat_template.jinja

@@ -0,0 +1,263 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- 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 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['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable: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 == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,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 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 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 -%}
+
+{%- set ns = namespace(prev_message_type=None) -%}
+{%- set loop_messages = messages -%}
+{{ bos_token }}
+{#- Handle System/Tool Definitions Block -#}
+{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
+    {{- '<|turn>system\n' -}}
+
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking is defined and enable_thinking -%}
+        {{- '<|think|>' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+
+    {%- if messages[0]['role'] in ['system', 'developer'] -%}
+        {{- messages[0]['content'] | trim -}}
+        {%- 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 %}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+        {{- '<|turn>' + role + '\n' }}
+
+            {%- if message['tool_calls'] -%}
+                {%- for tool_call in message['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 string -%}
+                        {{- function['arguments'] -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- if message['tool_responses'] -%}
+                {#- Tool Response handling -#}
+                {%- for tool_response in message['tool_responses'] -%}
+                    {{- '<|tool_response>' -}}
+                    {%- if tool_response['response'] is mapping -%}
+                        {{- 'response:' + tool_response['name'] | default('unknown') + '{' -}}
+                        {%- for key, value in tool_response['response'] | dictsort -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- if not loop.last %},{% endif -%}
+                        {%- endfor -%}
+                        {{- '}' -}}
+                    {%- else -%}
+                        {{- 'response:' + tool_response['name'] | default('unknown') + '{value:' + format_argument(tool_response['response'], escape_keys=False) + '}' -}}
+                    {%- endif -%}
+                    {{- '<tool_response|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_response' -%}
+            {%- endif -%}
+
+            {%- if message['content'] is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item['type'] == 'image' -%}
+                        {{- '\n\n<|image|>\n\n' -}}
+                        {%- set ns.prev_message_type = 'image' -%}
+                    {%- elif item['type'] == 'audio' -%}
+                        {{- '<|audio|>' -}}
+                        {%- set ns.prev_message_type = 'audio' -%}
+                    {%- elif item['type'] == 'video' -%}
+                        {{- '\n\n<|video|>\n\n' -}}
+                        {%- set ns.prev_message_type = 'video' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+        {%- if not (message['tool_responses'] and not message['content']) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<|turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,160 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "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": 32,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 64,
+    "head_dim": 32,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 8,
+    "hidden_size_per_layer_input": 2,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "layer_types": [
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 4,
+    "num_key_value_heads": 4,
+    "num_kv_shared_layers": 2,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": true,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "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": 8,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "vision_soft_tokens_per_image": 280
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.0",
+  "trust_remote_code": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2045c91d5ee53e379d6f3c4947b914c36ab4308f708e25858c2eb5bd694bc3
+size 9483948

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"
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,95 @@
+{
+  "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": 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<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
+  },
+  "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>"
+}