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 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,107 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248046,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": 248044,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": false,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 24,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_5",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "transformers_version": "5.5.0",
+  "use_cache": true
+}

metrics.jsonl

@@ -0,0 +1,16 @@
+{"step": 0, "phase": "init", "eval_stats": {"mean": 0.04923386165185366, "std": 0.0672960452300083, "p50": 0.022098293527960777, "min": 0.0004844925133511424, "max": 0.48668980598449707, "n": 500}, "king_stats": {"mean": 0.049498221530229786, "std": 0.06802473044304799, "p50": 0.022216019220650196, "min": 0.00043115520384162664, "max": 0.5087389349937439, "n": 500}, "ttest_init": {"p": 0.006664391975965393, "t": 2.483725779551327, "delta": 0.00026435987837612626}, "ts": "2026-04-15T20:58:56.696694+00:00"}
+{"step": 200, "lr_scale": 0.9993166823949923, "train_loss": 0.04409121069895466, "eval_stats": {"mean": 0.049311857622931714, "std": 0.06740049822603685, "p50": 0.02248609997332096, "min": 0.00048500997945666313, "max": 0.48793667554855347, "n": 500}, "ttest": {"p": 0.038884253398546245, "t": 1.7674232191084234, "delta": 0.00018636390729807317}, "time_s": 194.20898270606995, "ts": "2026-04-15T21:02:10.906022+00:00"}
+{"step": 400, "lr_scale": 0.9830206001391626, "train_loss": 0.09009218933351804, "eval_stats": {"mean": 0.049299912346992644, "std": 0.06738868575659439, "p50": 0.02272732648998499, "min": 0.0004841182380914688, "max": 0.490262508392334, "n": 500}, "ttest": {"p": 0.01876180816796784, "t": 2.085586056138108, "delta": 0.00019830918323714285}, "time_s": 403.67871284484863, "ts": "2026-04-15T21:05:40.375748+00:00"}
+{"step": 600, "lr_scale": 0.94576318804292, "train_loss": 0.03546153969628821, "eval_stats": {"mean": 0.049300457054632714, "std": 0.06737576218340464, "p50": 0.022611630149185658, "min": 0.00048297137254849076, "max": 0.4859647750854492, "n": 500}, "ttest": {"p": 0.03814927686852099, "t": 1.7762646608241186, "delta": 0.00019776447559706866}, "time_s": 579.6453504562378, "ts": "2026-04-15T21:08:36.342383+00:00"}
+{"step": 800, "lr_scale": 0.8893479743996033, "train_loss": 0.05191985557030421, "eval_stats": {"mean": 0.04928062827035319, "std": 0.06744980138721185, "p50": 0.022424165159463882, "min": 0.0004840348265133798, "max": 0.48707225918769836, "n": 500}, "ttest": {"p": 0.016905746565952087, "t": 2.1281808717118613, "delta": 0.00021759325987659396}, "time_s": 777.4084146022797, "ts": "2026-04-15T21:11:54.105437+00:00"}
+{"step": 1000, "lr_scale": 0.816505863699241, "train_loss": 0.0525697280267755, "eval_stats": {"mean": 0.04926518971985206, "std": 0.06744884865522346, "p50": 0.022657573223114014, "min": 0.00048476236406713724, "max": 0.48891204595565796, "n": 500}, "ttest": {"p": 0.015361488638152666, "t": 2.1667951964249412, "delta": 0.00023303181037772448}, "time_s": 942.2180001735687, "ts": "2026-04-15T21:14:38.915023+00:00"}
+{"step": 1200, "lr_scale": 0.7307629410938363, "train_loss": 0.06269996974636645, "eval_stats": {"mean": 0.04932236731104785, "std": 0.06747170791022622, "p50": 0.02260004822164774, "min": 0.0004863688664045185, "max": 0.48699474334716797, "n": 500}, "ttest": {"p": 0.05062384944610116, "t": 1.6418665347020596, "delta": 0.0001758542191819288}, "time_s": 1114.9673023223877, "ts": "2026-04-15T21:17:31.664326+00:00"}
+{"step": 1400, "lr_scale": 0.6362697843656823, "train_loss": 0.054507813227246515, "eval_stats": {"mean": 0.04921641759003978, "std": 0.06730569751655716, "p50": 0.022165304981172085, "min": 0.00048407434951514006, "max": 0.4873097240924835, "n": 500}, "ttest": {"p": 0.003951938791615225, "t": 2.6669084971505312, "delta": 0.0002818039401900023}, "time_s": 1317.0946643352509, "ts": "2026-04-15T21:20:53.791696+00:00"}
+{"step": 1600, "lr_scale": 0.5376005459343272, "train_loss": 0.05121549230534583, "eval_stats": {"mean": 0.04924376870249398, "std": 0.06731132677957478, "p50": 0.022301634773612022, "min": 0.00048451952170580626, "max": 0.4880450963973999, "n": 500}, "ttest": {"p": 0.008714042822885876, "t": 2.385499590630272, "delta": 0.000254452827735804}, "time_s": 1536.8934710025787, "ts": "2026-04-15T21:24:33.590503+00:00"}
+{"step": 1800, "lr_scale": 0.4395315307866404, "train_loss": 0.03267911489820108, "eval_stats": {"mean": 0.04932175885187462, "std": 0.06749503591443878, "p50": 0.02254238724708557, "min": 0.00048309314297512174, "max": 0.49090704321861267, "n": 500}, "ttest": {"p": 0.03723224677449167, "t": 1.787493684844929, "delta": 0.00017646267835516482}, "time_s": 1727.296855211258, "ts": "2026-04-15T21:27:43.993876+00:00"}
+{"step": 2000, "lr_scale": 0.3468099887600999, "train_loss": 0.0548671383789042, "eval_stats": {"mean": 0.04931762715277728, "std": 0.06743361479849123, "p50": 0.022715370170772076, "min": 0.0004832783597521484, "max": 0.48859840631484985, "n": 500}, "ttest": {"p": 0.04244454490907482, "t": 1.7264295996693089, "delta": 0.0001805943774525076}, "time_s": 1917.9054906368256, "ts": "2026-04-15T21:30:54.602515+00:00"}
+{"step": 2200, "lr_scale": 0.26392431330551447, "train_loss": 0.06741220635982852, "eval_stats": {"mean": 0.04933654265879886, "std": 0.06752193702561683, "p50": 0.022373460233211517, "min": 0.00048481530393473804, "max": 0.49078568816185, "n": 500}, "ttest": {"p": 0.05609729394387138, "t": 1.591214497600559, "delta": 0.0001616788714309223}, "time_s": 2092.1539630889893, "ts": "2026-04-15T21:33:48.850984+00:00"}
+{"step": 2400, "lr_scale": 0.19488677077162295, "train_loss": 0.06448472199917887, "eval_stats": {"mean": 0.049328347687376664, "std": 0.06751306919579182, "p50": 0.022689844481647015, "min": 0.00048434926429763436, "max": 0.4890824258327484, "n": 500}, "ttest": {"p": 0.044231922586760765, "t": 1.7068941151938304, "delta": 0.00016987384285312146}, "time_s": 2269.930186510086, "ts": "2026-04-15T21:36:46.627217+00:00"}
+{"step": 2600, "lr_scale": 0.14303927768609015, "train_loss": 0.05854208591626957, "eval_stats": {"mean": 0.049286155009642243, "std": 0.06745644118610092, "p50": 0.02254493534564972, "min": 0.00048245437210425735, "max": 0.48773133754730225, "n": 500}, "ttest": {"p": 0.017602023455660216, "t": 2.1117535271781587, "delta": 0.00021206652058754116}, "time_s": 2480.2628870010376, "ts": "2026-04-15T21:40:16.959909+00:00"}
+{"step": 2800, "lr_scale": 0.11089162781765398, "train_loss": 0.0502493919110358, "eval_stats": {"mean": 0.049311498976312575, "std": 0.06743956610237663, "p50": 0.022518017329275608, "min": 0.00048474076902493834, "max": 0.48754897713661194, "n": 500}, "ttest": {"p": 0.03433717967875091, "t": 1.8244997727938241, "delta": 0.0001867225539172068}, "time_s": 2649.7492282390594, "ts": "2026-04-15T21:43:06.446252+00:00"}
+{"step": 3000, "lr_scale": 0.1, "train_loss": 0.05227821274144974, "eval_stats": {"mean": 0.049290542708768044, "std": 0.06734368691165976, "p50": 0.022627292200922966, "min": 0.00048282850184477866, "max": 0.4875483214855194, "n": 500}, "ttest": {"p": 0.02278392421476271, "t": 2.0043927578831666, "delta": 0.00020767882146174087}, "time_s": 2865.3363506793976, "ts": "2026-04-15T21:46:42.033372+00:00"}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b469c345dc3a54f8420c2dfcd91ac93fde361095c3371d1f3d4be81381d7e5
+size 9682956989

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}