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

calibration_report.json

@@ -0,0 +1,309 @@
+{
+  "base_beta": 0.5402383208274841,
+  "base_bias": -0.4844930171966553,
+  "kept_epoch": 3,
+  "train": {
+    "uncalibrated": {
+      "nll": 0.13590236008167267,
+      "brier": 0.03834998607635498,
+      "ece": 0.008724160230938638,
+      "accuracy": 0.9460732936859131
+    },
+    "global_scaling": {
+      "nll": 0.1319091022014618,
+      "brier": 0.036343060433864594,
+      "ece": 0.024790527669744766,
+      "accuracy": 0.9506661891937256
+    },
+    "calibrated": {
+      "nll": 0.16371336579322815,
+      "brier": 0.045359522104263306,
+      "ece": 0.05632979728086318,
+      "accuracy": 0.9463504552841187
+    },
+    "beta": {
+      "mean": 0.3987804353237152,
+      "min": 0.021586544811725616,
+      "max": 0.6299230456352234
+    },
+    "bias": {
+      "mean": -0.60589200258255,
+      "min": -1.0286215543746948,
+      "max": 0.5900660753250122
+    },
+    "groups": {
+      "overconfident": {
+        "texts": 810,
+        "uncalibrated": {
+          "nll": 0.396918922662735,
+          "brier": 0.11602238565683365,
+          "ece": 0.1158942031665317,
+          "accuracy": 0.8361965417861938
+        },
+        "global_scaling": {
+          "nll": 0.2803961932659149,
+          "brier": 0.09336278587579727,
+          "ece": 0.07126283364916436,
+          "accuracy": 0.8470292091369629
+        },
+        "calibrated": {
+          "nll": 0.22382210195064545,
+          "brier": 0.07280737161636353,
+          "ece": 0.0505468512780157,
+          "accuracy": 0.8692417144775391
+        }
+      },
+      "underconfident": {
+        "texts": 952,
+        "uncalibrated": {
+          "nll": 0.18349525332450867,
+          "brier": 0.04817432537674904,
+          "ece": 0.0770668854550236,
+          "accuracy": 0.9513456225395203
+        },
+        "global_scaling": {
+          "nll": 0.21706710755825043,
+          "brier": 0.055873360484838486,
+          "ece": 0.09890477648015017,
+          "accuracy": 0.9416147470474243
+        },
+        "calibrated": {
+          "nll": 0.24962961673736572,
+          "brier": 0.06872871518135071,
+          "ece": 0.07814065774855061,
+          "accuracy": 0.9042116403579712
+        }
+      },
+      "mixed": {
+        "texts": 335,
+        "uncalibrated": {
+          "nll": 0.2900349199771881,
+          "brier": 0.0966075211763382,
+          "ece": 0.08953729352259154,
+          "accuracy": 0.8737332224845886
+        },
+        "global_scaling": {
+          "nll": 0.25439244508743286,
+          "brier": 0.08061423152685165,
+          "ece": 0.08066619354176002,
+          "accuracy": 0.8430566787719727
+        },
+        "calibrated": {
+          "nll": 0.2466566115617752,
+          "brier": 0.07597621530294418,
+          "ece": 0.049607173441170604,
+          "accuracy": 0.8896192908287048
+        }
+      },
+      "normal": {
+        "texts": 5655,
+        "uncalibrated": {
+          "nll": 0.03119591809809208,
+          "brier": 0.006655354518443346,
+          "ece": 0.024245568390645844,
+          "accuracy": 0.985680341720581
+        },
+        "global_scaling": {
+          "nll": 0.05599905923008919,
+          "brier": 0.010298365727066994,
+          "ece": 0.042321458578928245,
+          "accuracy": 0.9956013560295105
+        },
+        "calibrated": {
+          "nll": 0.1182105615735054,
+          "brier": 0.028781907632946968,
+          "ece": 0.07998285826653084,
+          "accuracy": 0.9845244884490967
+        }
+      }
+    },
+    "softmax": {
+      "texts": 6756,
+      "uncalibrated": {
+        "nll": 0.60243159532547,
+        "brier": 0.25821787118911743,
+        "ece": 0.08630393553886592,
+        "accuracy": 0.8288928270339966
+      },
+      "global_scaling": {
+        "nll": 0.47443029284477234,
+        "brier": 0.23971512913703918,
+        "ece": 0.035015895881971036,
+        "accuracy": 0.8288928270339966
+      },
+      "calibrated": {
+        "nll": 0.5013883709907532,
+        "brier": 0.25799572467803955,
+        "ece": 0.08973347695110602,
+        "accuracy": 0.8288928270339966
+      }
+    }
+  },
+  "held_out": {
+    "uncalibrated": {
+      "nll": 0.134813591837883,
+      "brier": 0.0394577793776989,
+      "ece": 0.009385065096777556,
+      "accuracy": 0.9442779421806335
+    },
+    "global_scaling": {
+      "nll": 0.1316956728696823,
+      "brier": 0.0370788536965847,
+      "ece": 0.024935297782987448,
+      "accuracy": 0.9489754438400269
+    },
+    "calibrated": {
+      "nll": 0.1662309616804123,
+      "brier": 0.046702150255441666,
+      "ece": 0.05650961722975578,
+      "accuracy": 0.9439539909362793
+    },
+    "beta": {
+      "mean": 0.39366212487220764,
+      "min": 0.023016568273305893,
+      "max": 0.6071414947509766
+    },
+    "bias": {
+      "mean": -0.5795870423316956,
+      "min": -1.0330911874771118,
+      "max": 0.5484000444412231
+    },
+    "groups": {
+      "overconfident": {
+        "texts": 180,
+        "uncalibrated": {
+          "nll": 0.5719922184944153,
+          "brier": 0.17103661596775055,
+          "ece": 0.17139117058701653,
+          "accuracy": 0.7580760717391968
+        },
+        "global_scaling": {
+          "nll": 0.401309609413147,
+          "brier": 0.1368330717086792,
+          "ece": 0.11016014898095755,
+          "accuracy": 0.7717157006263733
+        },
+        "calibrated": {
+          "nll": 0.31307777762413025,
+          "brier": 0.10509755462408066,
+          "ece": 0.07207305132336525,
+          "accuracy": 0.8083273768424988
+        }
+      },
+      "underconfident": {
+        "texts": 224,
+        "uncalibrated": {
+          "nll": 0.19197306036949158,
+          "brier": 0.05295313894748688,
+          "ece": 0.06992532354870229,
+          "accuracy": 0.9405063390731812
+        },
+        "global_scaling": {
+          "nll": 0.2224033921957016,
+          "brier": 0.0592648983001709,
+          "ece": 0.09383183797541672,
+          "accuracy": 0.9335442781448364
+        },
+        "calibrated": {
+          "nll": 0.2595052719116211,
+          "brier": 0.07272262871265411,
+          "ece": 0.07825523673930124,
+          "accuracy": 0.8962025046348572
+        }
+      },
+      "mixed": {
+        "texts": 97,
+        "uncalibrated": {
+          "nll": 0.29701313376426697,
+          "brier": 0.10088907927274704,
+          "ece": 0.10026825751042845,
+          "accuracy": 0.8682310581207275
+        },
+        "global_scaling": {
+          "nll": 0.2555745542049408,
+          "brier": 0.08258884400129318,
+          "ece": 0.08199416873906554,
+          "accuracy": 0.8375450968742371
+        },
+        "calibrated": {
+          "nll": 0.255821168422699,
+          "brier": 0.08022957295179367,
+          "ece": 0.04236628423505007,
+          "accuracy": 0.8835740089416504
+        }
+      },
+      "normal": {
+        "texts": 1436,
+        "uncalibrated": {
+          "nll": 0.028472088277339935,
+          "brier": 0.006469887215644121,
+          "ece": 0.022601176297401007,
+          "accuracy": 0.9865714907646179
+        },
+        "global_scaling": {
+          "nll": 0.052316512912511826,
+          "brier": 0.009927067905664444,
+          "ece": 0.04092645116679347,
+          "accuracy": 0.9967336058616638
+        },
+        "calibrated": {
+          "nll": 0.11164623498916626,
+          "brier": 0.02739347331225872,
+          "ece": 0.0744886720722503,
+          "accuracy": 0.9840309619903564
+        }
+      }
+    },
+    "softmax": {
+      "texts": 1709,
+      "uncalibrated": {
+        "nll": 0.5652890205383301,
+        "brier": 0.25095003843307495,
+        "ece": 0.08337326918689637,
+        "accuracy": 0.8338209390640259
+      },
+      "global_scaling": {
+        "nll": 0.4503483176231384,
+        "brier": 0.23204359412193298,
+        "ece": 0.036847078234715565,
+        "accuracy": 0.8338209390640259
+      },
+      "calibrated": {
+        "nll": 0.4841042459011078,
+        "brier": 0.25139153003692627,
+        "ece": 0.08952697261251302,
+        "accuracy": 0.8338209390640259
+      }
+    }
+  },
+  "args": {
+    "model_path": "models/qwen3.8-9b-fast/last",
+    "data_path": "data/decision_index_calibration.json",
+    "save_path": "models/qwen3.8-9b-fast/last-calibrated",
+    "eval_ratio": 0.2,
+    "max_examples": 10000,
+    "max_length": 2048,
+    "batch_size": 8,
+    "num_workers": 4,
+    "dtype": "bfloat16",
+    "hidden_size": 256,
+    "beta_max": 3.0,
+    "dropout": 0.1,
+    "prior_weight": 0.01,
+    "use_bias": true,
+    "bias_prior_weight": 0.01,
+    "skip_long": true,
+    "rank_preserving": true,
+    "early_stopping": null,
+    "objective": "mixed",
+    "softmax_weight": 0.5,
+    "balance_confidence": true,
+    "confidence_threshold": 0.7,
+    "num_epochs": 3,
+    "calibrator_batch_size": 64,
+    "lr": 0.0001,
+    "weight_decay": 0.01,
+    "patience": 3,
+    "seed": 42
+  }
+}

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 +1,256 @@
+{
+  "architecture_type": "decoder-kv",
+  "architectures": [
+    "GLiClassModel"
+  ],
+  "calibrator_beta_max": 3.0,
+  "calibrator_dropout": 0.1,
+  "calibrator_hidden_size": 256,
+  "calibrator_objective": "mixed",
+  "calibrator_rank_preserving": true,
+  "calibrator_use_bias": true,
+  "class_token_index": 248077,
+  "class_token_pooling": "first",
+  "contrastive_loss_coef": 0.0,
+  "dropout": 0.3,
+  "dtype": "bfloat16",
+  "embed_class_token": true,
+  "encoder_config": {
+    "_name_or_path": "Qwen/Qwen3.5-9B",
+    "architectures": [
+      "Qwen3_5ForConditionalGeneration"
+    ],
+    "image_token_id": 248056,
+    "model_type": "qwen3_5",
+    "text_config": {
+      "_name_or_path": "",
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "attn_output_gate": true,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "dtype": "bfloat16",
+      "eos_token_id": 248044,
+      "full_attention_interval": 4,
+      "head_dim": 256,
+      "hidden_act": "silu",
+      "hidden_size": 4096,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 12288,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "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,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "partial_rotary_factor": 0.25,
+      "problem_type": null,
+      "return_dict": true,
+      "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": true,
+      "vocab_size": 248080
+    },
+    "tie_word_embeddings": false,
+    "video_token_id": 248057,
+    "vision_config": {
+      "_name_or_path": "",
+      "architectures": null,
+      "chunk_size_feed_forward": 0,
+      "deepstack_visual_indexes": [],
+      "depth": 27,
+      "dtype": null,
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_size": 1152,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "in_channels": 3,
+      "initializer_range": 0.02,
+      "intermediate_size": 4304,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "model_type": "qwen3_5_vision",
+      "num_heads": 16,
+      "num_position_embeddings": 2304,
+      "out_hidden_size": 4096,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "patch_size": 16,
+      "problem_type": null,
+      "return_dict": true,
+      "rope_parameters": {
+        "rope_theta": 10000.0,
+        "rope_type": "axial"
+      },
+      "spatial_merge_size": 2,
+      "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+  },
+  "encoder_layer_id": -1,
+  "encoder_model_name": "Qwen/Qwen3.5-9B",
+  "eos_token_id": 248046,
+  "example_token_index": 248079,
+  "extract_text_features": false,
+  "focal_loss_alpha": 0.7,
+  "focal_loss_gamma": -1,
+  "focal_loss_reduction": "none",
+  "freeze_media_encoders": true,
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "initializer_range": 0.03,
+  "label_model_config": {
+    "_name_or_path": "BAAI/bge-small-en-v1.5",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "dtype": "float32",
+    "eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 384,
+    "id2label": {
+      "0": "LABEL_0"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0
+    },
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "bert",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "problem_type": null,
+    "return_dict": true,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 2,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "label_model_name": "BAAI/bge-small-en-v1.5",
+  "layer_wise": false,
+  "logit_scale_init_value": 2.6592,
+  "max_labels_alloc": "dynamic",
+  "max_num_classes": 25,
+  "model_type": "GLiClass",
+  "multimodal": true,
+  "normalize_features": false,
+  "pad_token_id": 248044,
+  "pooling_strategy": "avg",
+  "problem_type": "multi_label_classification",
+  "projector_hidden_act": "gelu",
+  "prompt_first": true,
+  "recurrent_bptt_steps": null,
+  "recurrent_confidence_coef": 0.0,
+  "recurrent_confidence_margin": 0.0,
+  "recurrent_confidence_mode": "relative",
+  "recurrent_halt_threshold": 0.01,
+  "recurrent_improvement_coef": 0.1,
+  "recurrent_improvement_margin": 0.05,
+  "recurrent_inference": true,
+  "recurrent_inference_max_steps": null,
+  "recurrent_min_steps": 1,
+  "recurrent_read_text": false,
+  "recurrent_steps": 3,
+  "scorer_attn_dropout": 0.1,
+  "scorer_encoder_num_layers": 2,
+  "scorer_full_sequence": false,
+  "scorer_mlp_hidden_size": 1024,
+  "scorer_num_heads": 16,
+  "scorer_type": "simple",
+  "sep_token_index": 248078,
+  "shuffle_labels": true,
+  "squeeze_layers": false,
+  "text_token_index": 248078,
+  "transformers_version": "5.19.0",
+  "use_calibrator": true,
+  "use_embedding_projection": false,
+  "use_lstm": false,
+  "use_segment_embeddings": false,
+  "vocab_size": 248080
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c457f1e8f9c01b5d233eba5858f9985341e49492144982deab3b10e416b961e4
+size 17968000418

processor_config.json

@@ -0,0 +1,61 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "max_video_tokens": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04472e9fcd4aea467a49025c27c0469a428bda2f812268fc9b26fea77c016f71
+size 19989897

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "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",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "merges_file": null,
+  "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+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen3_5Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}