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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' %}\n{% for message in messages %}\n    {#--- Handle User Messages with Template and Examples ---#}\n    {%- if message['role'] == 'user' and template -%}\n        {% if loop.first and message['role'] != 'system' %}\n            {{- '<|im_start|>system\\nYou are NuExtract, an information extraction tool created by NuMind.<|im_end|>' }}\n        {% endif %}\n    \n        {{- '<|im_start|>' + message['role'] -}}\n        \n        {#--- Template Section ---#}\n        {{ '\\n# Template:' }}\n        {{- '\\n' + template + '\\n' }}\n        \n        {#--- Examples Section (if provided) ---#}\n        {% if examples -%}\n            {{- '# Examples:' }}\n            {% for example in examples %}\n                {{- '## Input:\\n' }}\n                {#--- Handle image examples ---#}\n                {% if example['input'] is mapping and example['input']['type'] == 'image' %}\n                    {{- image_placeholder | trim -}}\n                {% elif example['input'] == '<image>' %}\n                    {{- image_placeholder | trim -}}\n                {% else %}\n                    {{- example['input'] -}}\n                {% endif %}\n                {{- '\\n## Output:\\n' ~ example['output'] }}\n            {% endfor %}\n        {%- endif %}\n        \n        {#--- Context Section: Handle various content types ---#}\n        {{- '# Context:\\n' }}\n        {%- if message['content'] is string -%}\n            {#--- Simple string content ---#}\n            {{- message['content'] | trim -}}\n        {%- elif message['content'] is mapping and message['content']['type'] == 'image' -%}\n            {#--- Single image document ---#}\n            {{- image_placeholder | trim -}}\n        {%- else -%}\n            {#--- List of content items (mixed text/images) ---#}\n            {#--- First, determine what the actual input content is (not ICL images) ---#}\n            {%- set ns = namespace(has_text_input=false, text_content='') -%}\n            \n            {#--- Count content types and identify actual input document ---#}\n            {%- for content in message['content'] -%}\n                {%- if content is mapping and content.get('type') == 'text' -%}\n                    {%- if content.get('text') != '<image>' -%}\n                        {%- set ns.has_text_input = true -%}\n                        {%- set ns.text_content = content['text'] -%}\n                    {%- endif -%}\n                {%- elif content is string -%}\n                    {%- if content != '<image>' -%}\n                        {%- set ns.has_text_input = true -%}\n                        {%- set ns.text_content = content -%}\n                    {%- endif -%}\n                {%- endif -%}\n            {%- endfor -%}\n            \n            {#--- Determine what to output based on actual input type ---#}\n            {%- if ns.has_text_input -%}\n                {#--- Main input is text, so output the text content ---#}\n                {{- ns.text_content | trim -}}\n            {%- else -%}\n                {#--- Main input is image or <image> placeholder ---#}\n                {%- set ns2 = namespace(found_image=false) -%}\n                {%- for content in message['content'] -%}\n                    {%- if content is mapping and content.get('type') == 'image' and not ns2.found_image -%}\n                        {{- image_placeholder | trim -}}\n                        {%- set ns2.found_image = true -%}\n                    {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' and not ns2.found_image -%}\n                        {{- image_placeholder | trim -}}\n                        {%- set ns2.found_image = true -%}\n                    {%- elif content is string and content == '<image>' and not ns2.found_image -%}\n                        {{- image_placeholder | trim -}}\n                        {%- set ns2.found_image = true -%}\n                    {%- endif -%}\n                {%- endfor -%}\n            {%- endif -%}\n        {%- endif -%}\n        {{- '<|im_end|>\\n'}}\n        \n    {#--- Handle All Other Messages (Assistant, System, etc.) ---#}\n    {% else %}\n        {% if loop.first and message['role'] != 'system' %}\n            {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>' }}\n        {% endif %}\n        \n        {{- '<|im_start|>' + message['role'] + '\\n' }}\n        \n        {#--- Same content handling logic as above but without template/examples ---#}\n        {%- if message['content'] is string -%}\n            {{- message['content'] | trim }}\n        {%- elif message['content'] is mapping and message['content']['type'] == 'image' -%}\n            {{- image_placeholder | trim }}\n        {%- else -%}\n            {%- set ns = namespace(found=false) -%}\n            {%- for content in message['content'] -%}\n                {%- if content is string -%}\n                    {{- content | trim -}}\n                {%- elif content is mapping and content.get('type') == 'text' -%}\n                    {{- content['text'] | trim -}}\n                {%- elif content is mapping and content.get('type') == 'image' -%}\n                    {# Skip adding image placeholder - it's already in the text #}\n                {%- endif -%}\n            {%- endfor -%}\n        {%- endif -%}\n        {{- '<|im_end|>'}}\n    {% endif %}\n{% endfor -%}\n{#--- Add Generation Prompt if Requested ---#}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant' }}\n{% endif -%}"
+}

config.json

@@ -0,0 +1,86 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": true,
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "damp_auto_increment": 0.0025,
+      "damp_percent": 0.01,
+      "mse": 0.0,
+      "quantizer": [
+        "gptqmodel:2.2.0"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel"
+    },
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f316f7d32005bf1d3cdea03bf96ea17162ca4d6e60e351979e7cd7bf52e30f3f
+size 3984201128

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbbcf658394272c859398721880f3d6ad9994faeb641234d983a837ff9557e68
+size 2944322576

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 2352000,
+  "merge_size": 2,
+  "min_pixels": 200704,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 2352000,
+    "shortest_edge": 200704
+  },
+  "temporal_patch_size": 2
+}

quant_log.csv

@@ -0,0 +1,197 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.22934364,0.01000,0.892
+0,self_attn.v_proj,0.03837002,0.01000,0.661
+0,self_attn.q_proj,1.04664111,0.01000,0.683
+0,self_attn.o_proj,0.18172245,0.01000,0.757
+0,mlp.up_proj,1.13388586,0.01000,0.656
+0,mlp.gate_proj,3.09285045,0.01000,0.665
+0,mlp.down_proj,0.35983995,0.01000,4.150
+1,self_attn.k_proj,0.15428428,0.01000,0.671
+1,self_attn.v_proj,0.03529196,0.01000,0.664
+1,self_attn.q_proj,0.55903387,0.01000,0.666
+1,self_attn.o_proj,0.04787841,0.01000,0.712
+1,mlp.up_proj,18.38950729,0.01000,0.704
+1,mlp.gate_proj,28.34197617,0.01000,0.689
+1,mlp.down_proj,0.70064735,0.01000,4.124
+2,self_attn.k_proj,0.65991199,0.01000,0.691
+2,self_attn.v_proj,0.10460287,0.01000,0.670
+2,self_attn.q_proj,2.31665039,0.01000,0.680
+2,self_attn.o_proj,0.11942939,0.01000,0.671
+2,mlp.up_proj,24.11547470,0.01000,0.712
+2,mlp.gate_proj,39.89593887,0.01000,0.708
+2,mlp.down_proj,1.31074762,0.01000,4.236
+3,self_attn.k_proj,0.84950960,0.01000,0.666
+3,self_attn.v_proj,0.19167003,0.01000,0.671
+3,self_attn.q_proj,3.01005602,0.01000,0.688
+3,self_attn.o_proj,0.32401937,0.01000,0.745
+3,mlp.up_proj,68.73696899,0.01000,0.708
+3,mlp.gate_proj,89.53257751,0.01000,0.708
+3,mlp.down_proj,0.00898164,0.01250,4.775
+4,self_attn.k_proj,1.53517699,0.01000,0.665
+4,self_attn.v_proj,0.40849376,0.01000,0.663
+4,self_attn.q_proj,6.51189804,0.01000,0.670
+4,self_attn.o_proj,0.26355922,0.01000,0.677
+4,mlp.up_proj,66.49259186,0.01000,0.707
+4,mlp.gate_proj,97.14162445,0.01000,0.705
+4,mlp.down_proj,1.66220617,0.01000,3.796
+5,self_attn.k_proj,1.43371511,0.01000,0.615
+5,self_attn.v_proj,0.50023222,0.01000,0.591
+5,self_attn.q_proj,6.66476917,0.01000,0.597
+5,self_attn.o_proj,0.30378860,0.01000,0.618
+5,mlp.up_proj,101.89800262,0.01000,0.638
+5,mlp.gate_proj,125.24084473,0.01000,0.627
+5,mlp.down_proj,1.60059404,0.01000,3.778
+6,self_attn.k_proj,0.92172015,0.01000,0.613
+6,self_attn.v_proj,0.42535174,0.01000,0.591
+6,self_attn.q_proj,4.48267555,0.01000,0.595
+6,self_attn.o_proj,0.36357266,0.01000,0.611
+6,mlp.up_proj,24.59759331,0.01000,0.624
+6,mlp.gate_proj,35.07592392,0.01000,0.638
+6,mlp.down_proj,2.50812578,0.01000,3.835
+7,self_attn.k_proj,1.01294935,0.01000,0.609
+7,self_attn.v_proj,0.77045107,0.01000,0.613
+7,self_attn.q_proj,5.43582582,0.01000,0.614
+7,self_attn.o_proj,0.80026621,0.01000,0.620
+7,mlp.up_proj,22.76921463,0.01000,0.628
+7,mlp.gate_proj,25.30647087,0.01000,0.629
+7,mlp.down_proj,3.32554030,0.01000,3.785
+8,self_attn.k_proj,1.85888863,0.01000,0.604
+8,self_attn.v_proj,0.64720315,0.01000,0.599
+8,self_attn.q_proj,8.09165096,0.01000,0.613
+8,self_attn.o_proj,0.81129563,0.01000,0.613
+8,mlp.up_proj,23.76294708,0.01000,0.626
+8,mlp.gate_proj,24.66311836,0.01000,0.645
+8,mlp.down_proj,3.01938772,0.01000,3.814
+9,self_attn.k_proj,1.35928941,0.01000,0.614
+9,self_attn.v_proj,0.89568245,0.01000,0.592
+9,self_attn.q_proj,7.29413176,0.01000,0.588
+9,self_attn.o_proj,1.05590606,0.01000,0.615
+9,mlp.up_proj,44.35252380,0.01000,0.630
+9,mlp.gate_proj,70.72398376,0.01000,0.624
+9,mlp.down_proj,2.76210523,0.01000,3.845
+10,self_attn.k_proj,1.23918748,0.01000,0.607
+10,self_attn.v_proj,0.55778021,0.01000,0.607
+10,self_attn.q_proj,6.26078033,0.01000,0.614
+10,self_attn.o_proj,0.77913922,0.01000,0.618
+10,mlp.up_proj,23.32112503,0.01000,0.634
+10,mlp.gate_proj,25.68299103,0.01000,0.638
+10,mlp.down_proj,2.54661942,0.01000,3.813
+11,self_attn.k_proj,1.53753209,0.01000,0.607
+11,self_attn.v_proj,0.51970351,0.01000,0.604
+11,self_attn.q_proj,6.50641966,0.01000,0.616
+11,self_attn.o_proj,0.92502165,0.01000,0.608
+11,mlp.up_proj,20.66933441,0.01000,0.638
+11,mlp.gate_proj,21.23263741,0.01000,0.635
+11,mlp.down_proj,2.25344348,0.01000,4.033
+12,self_attn.k_proj,1.53166485,0.01000,0.626
+12,self_attn.v_proj,0.64538920,0.01000,0.610
+12,self_attn.q_proj,6.94316101,0.01000,0.605
+12,self_attn.o_proj,0.87411481,0.01000,0.625
+12,mlp.up_proj,20.04409599,0.01000,0.652
+12,mlp.gate_proj,19.51464081,0.01000,0.637
+12,mlp.down_proj,2.57592607,0.01000,3.873
+13,self_attn.k_proj,1.32833993,0.01000,0.618
+13,self_attn.v_proj,0.81650221,0.01000,0.629
+13,self_attn.q_proj,7.09064341,0.01000,0.627
+13,self_attn.o_proj,1.31635439,0.01000,0.630
+13,mlp.up_proj,18.86554718,0.01000,0.611
+13,mlp.gate_proj,19.77309418,0.01000,0.610
+13,mlp.down_proj,2.35630417,0.01000,3.936
+14,self_attn.k_proj,1.82241821,0.01000,0.634
+14,self_attn.v_proj,0.73135352,0.01000,0.604
+14,self_attn.q_proj,9.67517090,0.01000,0.602
+14,self_attn.o_proj,1.25940311,0.01000,0.608
+14,mlp.up_proj,20.62960625,0.01000,0.645
+14,mlp.gate_proj,20.46133423,0.01000,0.616
+14,mlp.down_proj,2.82057142,0.01000,3.900
+15,self_attn.k_proj,1.70337152,0.01000,0.631
+15,self_attn.v_proj,0.67042011,0.01000,0.613
+15,self_attn.q_proj,7.78093481,0.01000,0.612
+15,self_attn.o_proj,1.17886329,0.01000,0.643
+15,mlp.up_proj,19.40904999,0.01000,0.653
+15,mlp.gate_proj,18.71631050,0.01000,0.644
+15,mlp.down_proj,2.82252669,0.01000,3.906
+16,self_attn.k_proj,1.62367511,0.01000,0.608
+16,self_attn.v_proj,0.81770545,0.01000,0.627
+16,self_attn.q_proj,8.22268105,0.01000,0.620
+16,self_attn.o_proj,1.57963610,0.01000,0.617
+16,mlp.up_proj,21.05099106,0.01000,0.628
+16,mlp.gate_proj,20.19021988,0.01000,0.608
+16,mlp.down_proj,2.81001258,0.01000,3.875
+17,self_attn.k_proj,1.57098889,0.01000,0.629
+17,self_attn.v_proj,0.99635255,0.01000,0.619
+17,self_attn.q_proj,8.82118225,0.01000,0.623
+17,self_attn.o_proj,1.32361174,0.01000,0.617
+17,mlp.up_proj,24.42174530,0.01000,0.646
+17,mlp.gate_proj,22.89795303,0.01000,0.641
+17,mlp.down_proj,3.81908369,0.01000,3.904
+18,self_attn.k_proj,1.23440194,0.01000,0.620
+18,self_attn.v_proj,1.10619903,0.01000,0.606
+18,self_attn.q_proj,7.51200390,0.01000,0.599
+18,self_attn.o_proj,1.73457372,0.01000,0.609
+18,mlp.up_proj,25.92087555,0.01000,0.643
+18,mlp.gate_proj,23.99379730,0.01000,0.640
+18,mlp.down_proj,4.36758852,0.01000,3.931
+19,self_attn.k_proj,1.25790572,0.01000,0.614
+19,self_attn.v_proj,1.34400010,0.01000,0.611
+19,self_attn.q_proj,8.63450813,0.01000,0.614
+19,self_attn.o_proj,1.89839542,0.01000,0.635
+19,mlp.up_proj,27.69528198,0.01000,0.645
+19,mlp.gate_proj,26.82501984,0.01000,0.648
+19,mlp.down_proj,4.74956894,0.01000,3.905
+20,self_attn.k_proj,1.25337625,0.01000,0.622
+20,self_attn.v_proj,1.42921281,0.01000,0.617
+20,self_attn.q_proj,7.67919111,0.01000,0.621
+20,self_attn.o_proj,1.30257142,0.01000,0.628
+20,mlp.up_proj,32.92043304,0.01000,0.629
+20,mlp.gate_proj,31.62638092,0.01000,0.638
+20,mlp.down_proj,8.67299080,0.01000,3.894
+21,self_attn.k_proj,1.36191201,0.01000,0.618
+21,self_attn.v_proj,2.07398558,0.01000,0.618
+21,self_attn.q_proj,8.82353687,0.01000,0.618
+21,self_attn.o_proj,3.09994173,0.01000,0.624
+21,mlp.up_proj,38.89333344,0.01000,0.637
+21,mlp.gate_proj,39.41935349,0.01000,0.638
+21,mlp.down_proj,11.07148075,0.01000,3.856
+22,self_attn.k_proj,1.76161993,0.01000,0.612
+22,self_attn.v_proj,3.56185842,0.01000,0.622
+22,self_attn.q_proj,11.30374718,0.01000,0.615
+22,self_attn.o_proj,3.15226030,0.01000,0.680
+22,mlp.up_proj,54.62146759,0.01000,0.651
+22,mlp.gate_proj,55.30439758,0.01000,0.639
+22,mlp.down_proj,21.54609680,0.01000,3.876
+23,self_attn.k_proj,2.53168511,0.01000,0.625
+23,self_attn.v_proj,6.27215004,0.01000,0.619
+23,self_attn.q_proj,15.55590439,0.01000,0.619
+23,self_attn.o_proj,8.35873032,0.01000,0.613
+23,mlp.up_proj,77.19926453,0.01000,0.635
+23,mlp.gate_proj,79.10525513,0.01000,0.631
+23,mlp.down_proj,28.26859283,0.01000,3.882
+24,self_attn.k_proj,2.05039835,0.01000,0.635
+24,self_attn.v_proj,6.27515268,0.01000,0.616
+24,self_attn.q_proj,14.22914314,0.01000,0.623
+24,self_attn.o_proj,3.39730763,0.01000,0.604
+24,mlp.up_proj,85.59671021,0.01000,0.635
+24,mlp.gate_proj,81.40880585,0.01000,0.619
+24,mlp.down_proj,39.02641296,0.01000,3.923
+25,self_attn.k_proj,2.47165418,0.01000,0.627
+25,self_attn.v_proj,10.35423660,0.01000,0.603
+25,self_attn.q_proj,16.47983932,0.01000,0.597
+25,self_attn.o_proj,6.00129890,0.01000,0.617
+25,mlp.up_proj,105.36215210,0.01000,0.627
+25,mlp.gate_proj,94.51289368,0.01000,0.619
+25,mlp.down_proj,53.65631866,0.01000,3.914
+26,self_attn.k_proj,3.47986841,0.01000,0.615
+26,self_attn.v_proj,25.66146660,0.01000,0.594
+26,self_attn.q_proj,27.72456932,0.01000,0.613
+26,self_attn.o_proj,14.51625061,0.01000,0.640
+26,mlp.up_proj,105.19096375,0.01000,0.652
+26,mlp.gate_proj,92.72835541,0.01000,0.626
+26,mlp.down_proj,0.00014774,0.01250,4.497
+27,self_attn.k_proj,3.90117908,0.01000,0.626
+27,self_attn.v_proj,36.91463470,0.01000,0.619
+27,self_attn.q_proj,42.00445557,0.01000,0.626
+27,self_attn.o_proj,25.07783699,0.01000,0.632
+27,mlp.up_proj,139.82276917,0.01000,0.650
+27,mlp.gate_proj,135.11968994,0.01000,0.643
+27,mlp.down_proj,280.19879150,0.01000,3.917

quantize_config.json

@@ -0,0 +1,21 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "desc_act": true,
+  "sym": true,
+  "lm_head": false,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:2.2.0"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.01,
+    "damp_auto_increment": 0.0025,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,212 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' %}\n{% for message in messages %}\n    {#--- Handle User Messages with Template and Examples ---#}\n    {%- if message['role'] == 'user' and template -%}\n        {% if loop.first and message['role'] != 'system' %}\n            {{- '<|im_start|>system\\nYou are NuExtract, an information extraction tool created by NuMind.<|im_end|>' }}\n        {% endif %}\n    \n        {{- '<|im_start|>' + message['role'] -}}\n        \n        {#--- Template Section ---#}\n        {{ '\\n# Template:' }}\n        {{- '\\n' + template + '\\n' }}\n        \n        {#--- Examples Section (if provided) ---#}\n        {% if examples -%}\n            {{- '# Examples:' }}\n            {% for example in examples %}\n                {{- '## Input:\\n' }}\n                {#--- Handle image examples ---#}\n                {% if example['input'] is mapping and example['input']['type'] == 'image' %}\n                    {{- image_placeholder | trim -}}\n                {% elif example['input'] == '<image>' %}\n                    {{- image_placeholder | trim -}}\n                {% else %}\n                    {{- example['input'] -}}\n                {% endif %}\n                {{- '\\n## Output:\\n' ~ example['output'] }}\n            {% endfor %}\n        {%- endif %}\n        \n        {#--- Context Section: Handle various content types ---#}\n        {{- '# Context:\\n' }}\n        {%- if message['content'] is string -%}\n            {#--- Simple string content ---#}\n            {{- message['content'] | trim -}}\n        {%- elif message['content'] is mapping and message['content']['type'] == 'image' -%}\n            {#--- Single image document ---#}\n            {{- image_placeholder | trim -}}\n        {%- else -%}\n            {#--- List of content items (mixed text/images) ---#}\n            {#--- First, determine what the actual input content is (not ICL images) ---#}\n            {%- set ns = namespace(has_text_input=false, text_content='') -%}\n            \n            {#--- Count content types and identify actual input document ---#}\n            {%- for content in message['content'] -%}\n                {%- if content is mapping and content.get('type') == 'text' -%}\n                    {%- if content.get('text') != '<image>' -%}\n                        {%- set ns.has_text_input = true -%}\n                        {%- set ns.text_content = content['text'] -%}\n                    {%- endif -%}\n                {%- elif content is string -%}\n                    {%- if content != '<image>' -%}\n                        {%- set ns.has_text_input = true -%}\n                        {%- set ns.text_content = content -%}\n                    {%- endif -%}\n                {%- endif -%}\n            {%- endfor -%}\n            \n            {#--- Determine what to output based on actual input type ---#}\n            {%- if ns.has_text_input -%}\n                {#--- Main input is text, so output the text content ---#}\n                {{- ns.text_content | trim -}}\n            {%- else -%}\n                {#--- Main input is image or <image> placeholder ---#}\n                {%- set ns2 = namespace(found_image=false) -%}\n                {%- for content in message['content'] -%}\n                    {%- if content is mapping and content.get('type') == 'image' and not ns2.found_image -%}\n                        {{- image_placeholder | trim -}}\n                        {%- set ns2.found_image = true -%}\n                    {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' and not ns2.found_image -%}\n                        {{- image_placeholder | trim -}}\n                        {%- set ns2.found_image = true -%}\n                    {%- elif content is string and content == '<image>' and not ns2.found_image -%}\n                        {{- image_placeholder | trim -}}\n                        {%- set ns2.found_image = true -%}\n                    {%- endif -%}\n                {%- endfor -%}\n            {%- endif -%}\n        {%- endif -%}\n        {{- '<|im_end|>\\n'}}\n        \n    {#--- Handle All Other Messages (Assistant, System, etc.) ---#}\n    {% else %}\n        {% if loop.first and message['role'] != 'system' %}\n            {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>' }}\n        {% endif %}\n        \n        {{- '<|im_start|>' + message['role'] + '\\n' }}\n        \n        {#--- Same content handling logic as above but without template/examples ---#}\n        {%- if message['content'] is string -%}\n            {{- message['content'] | trim }}\n        {%- elif message['content'] is mapping and message['content']['type'] == 'image' -%}\n            {{- image_placeholder | trim }}\n        {%- else -%}\n            {%- set ns = namespace(found=false) -%}\n            {%- for content in message['content'] -%}\n                {%- if content is string -%}\n                    {{- content | trim -}}\n                {%- elif content is mapping and content.get('type') == 'text' -%}\n                    {{- content['text'] | trim -}}\n                {%- elif content is mapping and content.get('type') == 'image' -%}\n                    {# Skip adding image placeholder - it's already in the text #}\n                {%- endif -%}\n            {%- endfor -%}\n        {%- endif -%}\n        {{- '<|im_end|>'}}\n    {% endif %}\n{% endfor -%}\n{#--- Add Generation Prompt if Requested ---#}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant' }}\n{% endif -%}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_pixels": 2352000,
+  "min_pixels": 200704,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}