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

chat_template.jinja

@@ -0,0 +1,351 @@
+{%- 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 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 -%}
+
+{%- 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|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if 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: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
+    {%- set prev_nt = namespace(role=None, found=false) -%}
+    {%- if loop.index0 > 0 -%}
+        {%- for j in range(loop.index0 - 1, -1, -1) -%}
+            {%- if not prev_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set prev_nt.role = loop_messages[j]['role'] -%}
+                    {%- set prev_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- set continue_same_model_turn = (role == 'model' and prev_nt.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') -%}
+    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- 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 -%}
+
+            {%- 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['tool_responses'] -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), 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') | default('unknown')) -%}
+                        {%- for tc in message['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) -}}
+                        {%- 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['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' -%}
+                        {{- '<|image|>' -}}
+                        {%- set ns.prev_message_type = 'image' -%}
+                    {%- elif item['type'] == 'audio' -%}
+                        {{- '<|audio|>' -}}
+                        {%- set ns.prev_message_type = 'audio' -%}
+                    {%- elif item['type'] == 'video' -%}
+                        {{- '<|video|>' -}}
+                        {%- set ns.prev_message_type = 'video' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif not (ns_tr_out.flag and not has_content) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,193 @@
+{
+  "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": 1024,
+    "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": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "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,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": 1,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_name": "jq/gemma4-e2b-fft-asr-uga",
+  "model_type": "gemma4",
+  "pad_token_id": 0,
+  "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": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1536,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_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": 35,
+    "num_key_value_heads": 1,
+    "num_kv_shared_layers": 20,
+    "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": true,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.0",
+  "unsloth_version": "2026.5.2",
+  "use_cache": false,
+  "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": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "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,
+    1,
+    106,
+    50
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.8.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6cc0002ac99d442c85e1d2cdd9b7577e61ecc0fb78d4409421e6b92e3464ce
+size 10208852910

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ee2f2ae8de49581bfeb04ce113841200a5b6fdd727c9383b4d28dadbf204e2
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e776e741fba5a953308d206a95e50abed2908736b9041a4ce113333636585ee
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d8bced9d66859cd2c3f4dcd8ab427197d4d46af3d9598b72af9fcf80b8392e
+size 32169781

tokenizer_config.json

@@ -0,0 +1,293 @@
+{
+  "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,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "max_length": null,
+  "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_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "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>",
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "46": {
+      "content": "<|tool>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "47": {
+      "content": "<tool|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "48": {
+      "content": "<|tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "49": {
+      "content": "<tool_call|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "50": {
+      "content": "<|tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "51": {
+      "content": "<tool_response|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "52": {
+      "content": "<|\"|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "98": {
+      "content": "<|think|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "100": {
+      "content": "<|channel>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "101": {
+      "content": "<channel|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "105": {
+      "content": "<|turn>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "106": {
+      "content": "<turn|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "255999": {
+      "content": "<|image>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "256000": {
+      "content": "<|audio>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "258880": {
+      "content": "<|image|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "258881": {
+      "content": "<|audio|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "258882": {
+      "content": "<image|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "258883": {
+      "content": "<audio|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "258884": {
+      "content": "<|video|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

trainer_state.json

@@ -0,0 +1,505 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 143,
+  "global_step": 572,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0175054704595186,
+      "grad_norm": 1.09375,
+      "learning_rate": 4.5e-06,
+      "loss": 0.3692042827606201,
+      "step": 10
+    },
+    {
+      "epoch": 0.0350109409190372,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.5e-06,
+      "loss": 0.35977413654327395,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525164113785558,
+      "grad_norm": 1.046875,
+      "learning_rate": 1.45e-05,
+      "loss": 0.36324713230133054,
+      "step": 30
+    },
+    {
+      "epoch": 0.0700218818380744,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.33168764114379884,
+      "step": 40
+    },
+    {
+      "epoch": 0.087527352297593,
+      "grad_norm": 0.828125,
+      "learning_rate": 2.45e-05,
+      "loss": 0.33778228759765627,
+      "step": 50
+    },
+    {
+      "epoch": 0.1050328227571116,
+      "grad_norm": 1.078125,
+      "learning_rate": 2.95e-05,
+      "loss": 0.2982091665267944,
+      "step": 60
+    },
+    {
+      "epoch": 0.12253829321663019,
+      "grad_norm": 0.859375,
+      "learning_rate": 3.45e-05,
+      "loss": 0.3437821626663208,
+      "step": 70
+    },
+    {
+      "epoch": 0.1400437636761488,
+      "grad_norm": 1.015625,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 0.29782021045684814,
+      "step": 80
+    },
+    {
+      "epoch": 0.1575492341356674,
+      "grad_norm": 0.6171875,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.30974411964416504,
+      "step": 90
+    },
+    {
+      "epoch": 0.175054704595186,
+      "grad_norm": 0.6796875,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.31342487335205077,
+      "step": 100
+    },
+    {
+      "epoch": 0.1925601750547046,
+      "grad_norm": 0.62890625,
+      "learning_rate": 4.995515841989726e-05,
+      "loss": 0.2926024436950684,
+      "step": 110
+    },
+    {
+      "epoch": 0.2100656455142232,
+      "grad_norm": 0.5703125,
+      "learning_rate": 4.9800356999122746e-05,
+      "loss": 0.2794817924499512,
+      "step": 120
+    },
+    {
+      "epoch": 0.2275711159737418,
+      "grad_norm": 0.98828125,
+      "learning_rate": 4.953572751052924e-05,
+      "loss": 0.32305901050567626,
+      "step": 130
+    },
+    {
+      "epoch": 0.24507658643326038,
+      "grad_norm": 0.99609375,
+      "learning_rate": 4.916244186246555e-05,
+      "loss": 0.29492759704589844,
+      "step": 140
+    },
+    {
+      "epoch": 0.25032822757111595,
+      "eval_text_loss": 1.3007618188858032,
+      "eval_text_model_preparation_time": 0.0138,
+      "eval_text_runtime": 5.3163,
+      "eval_text_samples_per_second": 11.286,
+      "eval_text_steps_per_second": 11.286,
+      "step": 143
+    },
+    {
+      "epoch": 0.25032822757111595,
+      "eval_audio_loss": 0.7166803479194641,
+      "eval_audio_model_preparation_time": 0.0138,
+      "eval_audio_runtime": 23.1192,
+      "eval_audio_samples_per_second": 5.753,
+      "eval_audio_steps_per_second": 5.753,
+      "step": 143
+    },
+    {
+      "epoch": 0.26258205689277897,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4.868215314571065e-05,
+      "loss": 0.31501500606536864,
+      "step": 150
+    },
+    {
+      "epoch": 0.2800875273522976,
+      "grad_norm": 0.609375,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.3073582649230957,
+      "step": 160
+    },
+    {
+      "epoch": 0.2975929978118162,
+      "grad_norm": 1.1171875,
+      "learning_rate": 4.74095387587539e-05,
+      "loss": 0.3264436960220337,
+      "step": 170
+    },
+    {
+      "epoch": 0.3150984682713348,
+      "grad_norm": 0.6796875,
+      "learning_rate": 4.662284884529549e-05,
+      "loss": 0.3189807653427124,
+      "step": 180
+    },
+    {
+      "epoch": 0.33260393873085337,
+      "grad_norm": 0.87109375,
+      "learning_rate": 4.5740402418755246e-05,
+      "loss": 0.3061279535293579,
+      "step": 190
+    },
+    {
+      "epoch": 0.350109409190372,
+      "grad_norm": 0.85546875,
+      "learning_rate": 4.476610738199053e-05,
+      "loss": 0.2863796234130859,
+      "step": 200
+    },
+    {
+      "epoch": 0.3676148796498906,
+      "grad_norm": 0.81640625,
+      "learning_rate": 4.370427838826934e-05,
+      "loss": 0.30284264087677004,
+      "step": 210
+    },
+    {
+      "epoch": 0.3851203501094092,
+      "grad_norm": 0.6796875,
+      "learning_rate": 4.2559617733882754e-05,
+      "loss": 0.28477931022644043,
+      "step": 220
+    },
+    {
+      "epoch": 0.4026258205689278,
+      "grad_norm": 1.2265625,
+      "learning_rate": 4.13371945340852e-05,
+      "loss": 0.29639883041381837,
+      "step": 230
+    },
+    {
+      "epoch": 0.4201312910284464,
+      "grad_norm": 0.7734375,
+      "learning_rate": 4.004242227458158e-05,
+      "loss": 0.30428614616394045,
+      "step": 240
+    },
+    {
+      "epoch": 0.437636761487965,
+      "grad_norm": 0.7890625,
+      "learning_rate": 3.868103483797414e-05,
+      "loss": 0.28317761421203613,
+      "step": 250
+    },
+    {
+      "epoch": 0.4551422319474836,
+      "grad_norm": 0.78515625,
+      "learning_rate": 3.725906111133579e-05,
+      "loss": 0.2817823886871338,
+      "step": 260
+    },
+    {
+      "epoch": 0.4726477024070022,
+      "grad_norm": 0.5859375,
+      "learning_rate": 3.578279828735983e-05,
+      "loss": 0.2978217601776123,
+      "step": 270
+    },
+    {
+      "epoch": 0.49015317286652077,
+      "grad_norm": 0.77734375,
+      "learning_rate": 3.4258783977321615e-05,
+      "loss": 0.28665401935577395,
+      "step": 280
+    },
+    {
+      "epoch": 0.5006564551422319,
+      "eval_text_loss": 1.2351676225662231,
+      "eval_text_model_preparation_time": 0.0138,
+      "eval_text_runtime": 5.5155,
+      "eval_text_samples_per_second": 10.878,
+      "eval_text_steps_per_second": 10.878,
+      "step": 286
+    },
+    {
+      "epoch": 0.5006564551422319,
+      "eval_audio_loss": 0.7075363397598267,
+      "eval_audio_model_preparation_time": 0.0138,
+      "eval_audio_runtime": 24.8383,
+      "eval_audio_samples_per_second": 5.355,
+      "eval_audio_steps_per_second": 5.355,
+      "step": 286
+    },
+    {
+      "epoch": 0.5076586433260394,
+      "grad_norm": 0.91015625,
+      "learning_rate": 3.2693767259349574e-05,
+      "loss": 0.30377969741821287,
+      "step": 290
+    },
+    {
+      "epoch": 0.5251641137855579,
+      "grad_norm": 0.72265625,
+      "learning_rate": 3.109467879021793e-05,
+      "loss": 0.2989386320114136,
+      "step": 300
+    },
+    {
+      "epoch": 0.5426695842450766,
+      "grad_norm": 0.765625,
+      "learning_rate": 2.9468600113020715e-05,
+      "loss": 0.2834346771240234,
+      "step": 310
+    },
+    {
+      "epoch": 0.5601750547045952,
+      "grad_norm": 0.80859375,
+      "learning_rate": 2.7822732296647548e-05,
+      "loss": 0.3039692401885986,
+      "step": 320
+    },
+    {
+      "epoch": 0.5776805251641138,
+      "grad_norm": 0.8046875,
+      "learning_rate": 2.6164364045941042e-05,
+      "loss": 0.3042268753051758,
+      "step": 330
+    },
+    {
+      "epoch": 0.5951859956236324,
+      "grad_norm": 0.70703125,
+      "learning_rate": 2.450083942375939e-05,
+      "loss": 0.2903634548187256,
+      "step": 340
+    },
+    {
+      "epoch": 0.612691466083151,
+      "grad_norm": 0.6328125,
+      "learning_rate": 2.2839525327886768e-05,
+      "loss": 0.2882160425186157,
+      "step": 350
+    },
+    {
+      "epoch": 0.6301969365426696,
+      "grad_norm": 0.98046875,
+      "learning_rate": 2.1187778866819505e-05,
+      "loss": 0.2965713024139404,
+      "step": 360
+    },
+    {
+      "epoch": 0.6477024070021882,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.955291477890399e-05,
+      "loss": 0.2957930564880371,
+      "step": 370
+    },
+    {
+      "epoch": 0.6652078774617067,
+      "grad_norm": 0.83203125,
+      "learning_rate": 1.7942173039110305e-05,
+      "loss": 0.299970006942749,
+      "step": 380
+    },
+    {
+      "epoch": 0.6827133479212254,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.6362686796894435e-05,
+      "loss": 0.2794990062713623,
+      "step": 390
+    },
+    {
+      "epoch": 0.700218818380744,
+      "grad_norm": 0.48046875,
+      "learning_rate": 1.4821450787136037e-05,
+      "loss": 0.28992691040039065,
+      "step": 400
+    },
+    {
+      "epoch": 0.7177242888402626,
+      "grad_norm": 0.640625,
+      "learning_rate": 1.332529035404327e-05,
+      "loss": 0.28732025623321533,
+      "step": 410
+    },
+    {
+      "epoch": 0.7352297592997812,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.1880831225202247e-05,
+      "loss": 0.2870940685272217,
+      "step": 420
+    },
+    {
+      "epoch": 0.750984682713348,
+      "eval_text_loss": 1.21077561378479,
+      "eval_text_model_preparation_time": 0.0138,
+      "eval_text_runtime": 5.0709,
+      "eval_text_samples_per_second": 11.832,
+      "eval_text_steps_per_second": 11.832,
+      "step": 429
+    },
+    {
+      "epoch": 0.750984682713348,
+      "eval_audio_loss": 0.698564350605011,
+      "eval_audio_model_preparation_time": 0.0138,
+      "eval_audio_runtime": 22.6597,
+      "eval_audio_samples_per_second": 5.869,
+      "eval_audio_steps_per_second": 5.869,
+      "step": 429
+    },
+    {
+      "epoch": 0.7527352297592997,
+      "grad_norm": 0.78125,
+      "learning_rate": 1.049447016962597e-05,
+      "loss": 0.29113962650299074,
+      "step": 430
+    },
+    {
+      "epoch": 0.7702407002188184,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.172346669743626e-06,
+      "loss": 0.27481784820556643,
+      "step": 440
+    },
+    {
+      "epoch": 0.787746170678337,
+      "grad_norm": 0.81640625,
+      "learning_rate": 7.920315732780126e-06,
+      "loss": 0.2930293560028076,
+      "step": 450
+    },
+    {
+      "epoch": 0.8052516411378556,
+      "grad_norm": 0.578125,
+      "learning_rate": 6.743921961930549e-06,
+      "loss": 0.28920702934265136,
+      "step": 460
+    },
+    {
+      "epoch": 0.8227571115973742,
+      "grad_norm": 0.71875,
+      "learning_rate": 5.648375002154879e-06,
+      "loss": 0.28770692348480226,
+      "step": 470
+    },
+    {
+      "epoch": 0.8402625820568927,
+      "grad_norm": 0.56640625,
+      "learning_rate": 4.6385264693311305e-06,
+      "loss": 0.2829106330871582,
+      "step": 480
+    },
+    {
+      "epoch": 0.8577680525164114,
+      "grad_norm": 0.7421875,
+      "learning_rate": 3.7188484649356562e-06,
+      "loss": 0.29122676849365237,
+      "step": 490
+    },
+    {
+      "epoch": 0.87527352297593,
+      "grad_norm": 0.8046875,
+      "learning_rate": 2.8934137713982454e-06,
+      "loss": 0.29016549587249757,
+      "step": 500
+    },
+    {
+      "epoch": 0.8927789934354485,
+      "grad_norm": 0.87890625,
+      "learning_rate": 2.1658778158365284e-06,
+      "loss": 0.29710874557495115,
+      "step": 510
+    },
+    {
+      "epoch": 0.9102844638949672,
+      "grad_norm": 1.0234375,
+      "learning_rate": 1.5394624820432079e-06,
+      "loss": 0.2932096004486084,
+      "step": 520
+    },
+    {
+      "epoch": 0.9277899343544858,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.01694184241429e-06,
+      "loss": 0.28654632568359373,
+      "step": 530
+    },
+    {
+      "epoch": 0.9452954048140044,
+      "grad_norm": 0.57421875,
+      "learning_rate": 6.006298730045601e-07,
+      "loss": 0.2893019676208496,
+      "step": 540
+    },
+    {
+      "epoch": 0.962800875273523,
+      "grad_norm": 0.70703125,
+      "learning_rate": 2.923702061138206e-07,
+      "loss": 0.2885005235671997,
+      "step": 550
+    },
+    {
+      "epoch": 0.9803063457330415,
+      "grad_norm": 0.5546875,
+      "learning_rate": 9.352796578453172e-08,
+      "loss": 0.30120275020599363,
+      "step": 560
+    },
+    {
+      "epoch": 0.9978118161925602,
+      "grad_norm": 0.5078125,
+      "learning_rate": 4.983722367229993e-09,
+      "loss": 0.2859893083572388,
+      "step": 570
+    },
+    {
+      "epoch": 1.0,
+      "eval_text_loss": 1.2087676525115967,
+      "eval_text_model_preparation_time": 0.0138,
+      "eval_text_runtime": 5.4583,
+      "eval_text_samples_per_second": 10.992,
+      "eval_text_steps_per_second": 10.992,
+      "step": 572
+    },
+    {
+      "epoch": 1.0,
+      "eval_audio_loss": 0.6977604627609253,
+      "eval_audio_model_preparation_time": 0.0138,
+      "eval_audio_runtime": 22.5218,
+      "eval_audio_samples_per_second": 5.905,
+      "eval_audio_steps_per_second": 5.905,
+      "step": 572
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 572,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 12,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.96093256353648e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6906c2dd0f60d842f35c319522ede5e9054fb9019c882a25267a2d08f135ce09
+size 5905