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 +1,263 @@
+{%- 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 +1,117 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": null,
+  "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": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "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",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "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": 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": 42,
+    "num_key_value_heads": 2,
+    "num_kv_shared_layers": 18,
+    "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": "5.6.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": null,
+  "vision_soft_tokens_per_image": 280
+}

crossbreed_report.json

@@ -0,0 +1,425 @@
+{
+  "method": "Darwin V6 FFN Cross-Architecture Breeding",
+  "father": "FINAL-Bench/Darwin-4B-David",
+  "mother": "Qwen/Qwen3.5-4B",
+  "best_score": 0.8600000000000001,
+  "best_genome": {
+    "layer_ratios": [
+      0.20647537706794558,
+      0.14823192392605827,
+      0.0,
+      0.17255649055377628,
+      0.13624945227921445,
+      0.01479710117133131,
+      0.08801326081040438,
+      0.0,
+      0.06046052630532496,
+      0.056009156141461305,
+      0.0024092496762064264,
+      0.1261309679397987,
+      0.04828750057970729,
+      0.053275827295554884,
+      0.15780548864527766,
+      0.0,
+      0.0,
+      0.14072768357469992,
+      0.0,
+      0.14538068622584463,
+      0.06922625936437449,
+      0.111020864912764,
+      0.0,
+      0.0,
+      0.0,
+      0.0,
+      0.05803946391147091,
+      0.07135313327306363,
+      0.0,
+      0.2911474201445217,
+      0.19313766748231753,
+      0.24353827123418265,
+      0.2733483853035385,
+      0.2552905188846425,
+      0.24517950479346443,
+      0.17269703961840893,
+      0.05182227315946832,
+      0.1261048170624301,
+      0.030886470312547362,
+      0.30040019496717263,
+      0.01853314361778055,
+      0.18194639710507124
+    ],
+    "frozen_layers": [
+      15,
+      16,
+      22,
+      23,
+      24,
+      25
+    ]
+  },
+  "frozen_layers": [
+    15,
+    16,
+    22,
+    23,
+    24,
+    25
+  ],
+  "father_layers": 42,
+  "mother_layers": 32,
+  "blend_dim": 9216,
+  "population": 10,
+  "steps": 50,
+  "history": [
+    {
+      "step": 1,
+      "best_score": 0.8033333333333333,
+      "step_best": 0.8033333333333333,
+      "mean_ratio": 0.06290678970639335,
+      "sigma": 0.0634404317603052
+    },
+    {
+      "step": 2,
+      "best_score": 0.8333333333333334,
+      "step_best": 0.8333333333333334,
+      "mean_ratio": 0.07781023986570348,
+      "sigma": 0.0646884194918551
+    },
+    {
+      "step": 3,
+      "best_score": 0.8333333333333334,
+      "step_best": 0.8333333333333334,
+      "mean_ratio": 0.08880605810847592,
+      "sigma": 0.06783077008249229
+    },
+    {
+      "step": 4,
+      "best_score": 0.8333333333333334,
+      "step_best": 0.8333333333333334,
+      "mean_ratio": 0.0875377099665294,
+      "sigma": 0.07246831497330888
+    },
+    {
+      "step": 5,
+      "best_score": 0.8333333333333334,
+      "step_best": 0.8333333333333334,
+      "mean_ratio": 0.07235673891852008,
+      "sigma": 0.07355498738778984
+    },
+    {
+      "step": 6,
+      "best_score": 0.8333333333333334,
+      "step_best": 0.8333333333333334,
+      "mean_ratio": 0.08893151321934065,
+      "sigma": 0.07863044719946359
+    },
+    {
+      "step": 7,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8600000000000001,
+      "mean_ratio": 0.10224743557856028,
+      "sigma": 0.08705722955505009
+    },
+    {
+      "step": 8,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8333333333333334,
+      "mean_ratio": 0.10904590150041411,
+      "sigma": 0.10103246785714566
+    },
+    {
+      "step": 9,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8333333333333334,
+      "mean_ratio": 0.12075370728399674,
+      "sigma": 0.11337025202197282
+    },
+    {
+      "step": 10,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8600000000000001,
+      "mean_ratio": 0.12633176528207413,
+      "sigma": 0.11807554992374279
+    },
+    {
+      "step": 11,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8066666666666666,
+      "mean_ratio": 0.1360039520684083,
+      "sigma": 0.12052408658697357
+    },
+    {
+      "step": 12,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8600000000000001,
+      "mean_ratio": 0.13936414687282414,
+      "sigma": 0.1289517265467281
+    },
+    {
+      "step": 13,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8066666666666666,
+      "mean_ratio": 0.14874480886048833,
+      "sigma": 0.13549734195764399
+    },
+    {
+      "step": 14,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8600000000000001,
+      "mean_ratio": 0.13908605940040214,
+      "sigma": 0.140514158071659
+    },
+    {
+      "step": 15,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8600000000000001,
+      "mean_ratio": 0.15050216822758744,
+      "sigma": 0.13797636310450967
+    },
+    {
+      "step": 16,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8333333333333334,
+      "mean_ratio": 0.14460856892680315,
+      "sigma": 0.14159146100351827
+    },
+    {
+      "step": 17,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8033333333333333,
+      "mean_ratio": 0.16025742024472867,
+      "sigma": 0.1422776654358227
+    },
+    {
+      "step": 18,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8300000000000001,
+      "mean_ratio": 0.15554231513226557,
+      "sigma": 0.13420694226282484
+    },
+    {
+      "step": 19,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8066666666666666,
+      "mean_ratio": 0.14643616444218682,
+      "sigma": 0.13023324254225802
+    },
+    {
+      "step": 20,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8066666666666666,
+      "mean_ratio": 0.14936636321246355,
+      "sigma": 0.12533258523547494
+    },
+    {
+      "step": 21,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7766666666666666,
+      "mean_ratio": 0.1534663446960059,
+      "sigma": 0.13762706492711088
+    },
+    {
+      "step": 22,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.75,
+      "mean_ratio": 0.1627801122395406,
+      "sigma": 0.1505341747990411
+    },
+    {
+      "step": 23,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8333333333333334,
+      "mean_ratio": 0.15923176743481993,
+      "sigma": 0.14799216541987317
+    },
+    {
+      "step": 24,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7766666666666666,
+      "mean_ratio": 0.1677333219026785,
+      "sigma": 0.14774402574980733
+    },
+    {
+      "step": 25,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7733333333333333,
+      "mean_ratio": 0.16422066609570704,
+      "sigma": 0.13843034269180055
+    },
+    {
+      "step": 26,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7733333333333333,
+      "mean_ratio": 0.13906027861386117,
+      "sigma": 0.13242693786187337
+    },
+    {
+      "step": 27,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7466666666666666,
+      "mean_ratio": 0.15264091379157918,
+      "sigma": 0.12790371883066087
+    },
+    {
+      "step": 28,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7766666666666666,
+      "mean_ratio": 0.15489601769619152,
+      "sigma": 0.12755566453158676
+    },
+    {
+      "step": 29,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8300000000000001,
+      "mean_ratio": 0.1569011973937426,
+      "sigma": 0.1408499857258934
+    },
+    {
+      "step": 30,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8033333333333333,
+      "mean_ratio": 0.15239983824794084,
+      "sigma": 0.1401183829818277
+    },
+    {
+      "step": 31,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.75,
+      "mean_ratio": 0.16504790158283703,
+      "sigma": 0.1397318196414391
+    },
+    {
+      "step": 32,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7166666666666666,
+      "mean_ratio": 0.17022579569707286,
+      "sigma": 0.14776185561134852
+    },
+    {
+      "step": 33,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.75,
+      "mean_ratio": 0.16990917826740068,
+      "sigma": 0.1511193869383969
+    },
+    {
+      "step": 34,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.75,
+      "mean_ratio": 0.1662469295861985,
+      "sigma": 0.14280401329995637
+    },
+    {
+      "step": 35,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7233333333333334,
+      "mean_ratio": 0.15841638718823015,
+      "sigma": 0.14253965477777314
+    },
+    {
+      "step": 36,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7766666666666666,
+      "mean_ratio": 0.15146795147357647,
+      "sigma": 0.1439933714094963
+    },
+    {
+      "step": 37,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.69,
+      "mean_ratio": 0.16384951542843323,
+      "sigma": 0.14494179174105692
+    },
+    {
+      "step": 38,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.75,
+      "mean_ratio": 0.1537324421566684,
+      "sigma": 0.14168105367926756
+    },
+    {
+      "step": 39,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.6633333333333333,
+      "mean_ratio": 0.15970050125209775,
+      "sigma": 0.14510887362344935
+    },
+    {
+      "step": 40,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.75,
+      "mean_ratio": 0.17459025377647835,
+      "sigma": 0.14284720765256412
+    },
+    {
+      "step": 41,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7166666666666666,
+      "mean_ratio": 0.17482397301205677,
+      "sigma": 0.141806358821768
+    },
+    {
+      "step": 42,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8066666666666666,
+      "mean_ratio": 0.17565062165216766,
+      "sigma": 0.13769978752156617
+    },
+    {
+      "step": 43,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.78,
+      "mean_ratio": 0.18855555348725378,
+      "sigma": 0.154657603603785
+    },
+    {
+      "step": 44,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.69,
+      "mean_ratio": 0.19082400740817784,
+      "sigma": 0.1574354863056092
+    },
+    {
+      "step": 45,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.6866666666666666,
+      "mean_ratio": 0.19942602590353126,
+      "sigma": 0.15601461390541457
+    },
+    {
+      "step": 46,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.69,
+      "mean_ratio": 0.20906959596828187,
+      "sigma": 0.17428205146474535
+    },
+    {
+      "step": 47,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.75,
+      "mean_ratio": 0.20388207036040726,
+      "sigma": 0.17887711098551665
+    },
+    {
+      "step": 48,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.7166666666666666,
+      "mean_ratio": 0.20167068354690648,
+      "sigma": 0.16735493919167624
+    },
+    {
+      "step": 49,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8066666666666666,
+      "mean_ratio": 0.19931687316581534,
+      "sigma": 0.16107798896733172
+    },
+    {
+      "step": 50,
+      "best_score": 0.8600000000000001,
+      "step_best": 0.8300000000000001,
+      "mean_ratio": 0.17980169993450223,
+      "sigma": 0.15804274374915395
+    }
+  ]
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "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": "5.6.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55c85d7d21c6ec45de9cded3d8e444e1a19dbdebba36994a76e75db5a72373b
+size 15036233372

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c18ffebe9ef41e463a6c99b4a23736b91ed4a2588cbfe761fef29bfd3688cf
+size 32169725

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>"
+}