Upload folder using huggingface_hub

chat_template.json

@@ -1,3 +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 -%}"
+  "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            {%- for content in message['content'] -%}\n                {%- if content is string -%}\n                    {{- content | trim -}}\n                {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' -%}\n                    {{- image_placeholder | 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 -%}"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f316f7d32005bf1d3cdea03bf96ea17162ca4d6e60e351979e7cd7bf52e30f3f
+oid sha256:c031e6ade26c8bd2f3ebb988be752737479f30658c76e6738b90d7099dd7f4a5
 size 3984201128

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbbcf658394272c859398721880f3d6ad9994faeb641234d983a837ff9557e68
+oid sha256:b377f9bec88da826022e7a0b469bd3189a45b4716b7587ac902aaed1a175ce68
 size 2944322576

preprocessor_config.json

@@ -14,7 +14,7 @@
     0.26130258,
     0.27577711
   ],
-  "max_pixels": 2352000,
+  "max_pixels": 23000000,
   "merge_size": 2,
   "min_pixels": 200704,
   "patch_size": 14,
@@ -22,7 +22,7 @@
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "longest_edge": 2352000,
+    "longest_edge": 23000000,
     "shortest_edge": 200704
   },
   "temporal_patch_size": 2

quant_log.csv

@@ -1,197 +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
+0,self_attn.k_proj,0.37272908,0.01000,0.963
+0,self_attn.v_proj,0.06249057,0.01000,0.568
+0,self_attn.q_proj,1.71414546,0.01000,0.582
+0,self_attn.o_proj,0.27218719,0.01000,0.579
+0,mlp.up_proj,1.97148761,0.01000,0.602
+0,mlp.gate_proj,5.45231162,0.01000,0.596
+0,mlp.down_proj,0.61297246,0.01000,3.775
+1,self_attn.k_proj,0.27201448,0.01000,0.597
+1,self_attn.v_proj,0.06198664,0.01000,0.593
+1,self_attn.q_proj,0.98380148,0.01000,0.580
+1,self_attn.o_proj,0.07505655,0.01000,0.641
+1,mlp.up_proj,29.94800979,0.01000,0.609
+1,mlp.gate_proj,46.14816320,0.01000,0.605
+1,mlp.down_proj,1.18726570,0.01000,3.571
+2,self_attn.k_proj,1.10431638,0.01000,0.573
+2,self_attn.v_proj,0.17621659,0.01000,0.580
+2,self_attn.q_proj,3.89487222,0.01000,0.582
+2,self_attn.o_proj,0.19335656,0.01000,0.599
+2,mlp.up_proj,39.82002804,0.01000,0.599
+2,mlp.gate_proj,65.63606855,0.01000,0.596
+2,mlp.down_proj,2.19458135,0.01000,3.704
+3,self_attn.k_proj,1.41276497,0.01000,0.583
+3,self_attn.v_proj,0.32184546,0.01000,0.565
+3,self_attn.q_proj,5.03698810,0.01000,0.568
+3,self_attn.o_proj,0.52726446,0.01000,0.599
+3,mlp.up_proj,114.33669945,0.01000,0.638
+3,mlp.gate_proj,148.85794254,0.01000,0.621
+3,mlp.down_proj,0.01009648,0.01250,4.438
+4,self_attn.k_proj,2.52166661,0.01000,0.639
+4,self_attn.v_proj,0.67622127,0.01000,0.620
+4,self_attn.q_proj,10.74245164,0.01000,0.600
+4,self_attn.o_proj,0.42747642,0.01000,0.602
+4,mlp.up_proj,110.46822172,0.01000,0.661
+4,mlp.gate_proj,161.16622643,0.01000,0.668
+4,mlp.down_proj,2.72548815,0.01000,3.644
+5,self_attn.k_proj,2.36542153,0.01000,0.596
+5,self_attn.v_proj,0.82987875,0.01000,0.580
+5,self_attn.q_proj,10.98670529,0.01000,0.583
+5,self_attn.o_proj,0.48163516,0.01000,0.578
+5,mlp.up_proj,169.33053275,0.01000,0.606
+5,mlp.gate_proj,208.03480575,0.01000,0.632
+5,mlp.down_proj,2.63673970,0.01000,3.785
+6,self_attn.k_proj,1.51797450,0.01000,0.567
+6,self_attn.v_proj,0.70319183,0.01000,0.574
+6,self_attn.q_proj,7.39946994,0.01000,0.575
+6,self_attn.o_proj,0.58445273,0.01000,0.597
+6,mlp.up_proj,40.56810539,0.01000,0.589
+6,mlp.gate_proj,57.70911391,0.01000,0.594
+6,mlp.down_proj,4.15842980,0.01000,3.864
+7,self_attn.k_proj,1.65347762,0.01000,0.605
+7,self_attn.v_proj,1.26919441,0.01000,0.621
+7,self_attn.q_proj,8.91557116,0.01000,0.617
+7,self_attn.o_proj,1.26652386,0.01000,0.634
+7,mlp.up_proj,37.50803346,0.01000,0.644
+7,mlp.gate_proj,41.65068270,0.01000,0.663
+7,mlp.down_proj,5.51070028,0.01000,3.738
+8,self_attn.k_proj,3.05815341,0.01000,0.599
+8,self_attn.v_proj,1.05918791,0.01000,0.605
+8,self_attn.q_proj,13.26367949,0.01000,0.607
+8,self_attn.o_proj,1.30098944,0.01000,0.605
+8,mlp.up_proj,39.01938902,0.01000,0.591
+8,mlp.gate_proj,40.47557959,0.01000,0.582
+8,mlp.down_proj,5.03287961,0.01000,3.769
+9,self_attn.k_proj,2.22347360,0.01000,0.609
+9,self_attn.v_proj,1.48193391,0.01000,0.608
+9,self_attn.q_proj,11.94389274,0.01000,0.585
+9,self_attn.o_proj,1.67733308,0.01000,0.602
+9,mlp.up_proj,72.89947883,0.01000,0.633
+9,mlp.gate_proj,116.10071928,0.01000,0.614
+9,mlp.down_proj,4.55470750,0.01000,3.589
+10,self_attn.k_proj,2.02291953,0.01000,0.587
+10,self_attn.v_proj,0.91743158,0.01000,0.572
+10,self_attn.q_proj,10.23927115,0.01000,0.586
+10,self_attn.o_proj,1.26303708,0.01000,0.628
+10,mlp.up_proj,38.33327576,0.01000,0.631
+10,mlp.gate_proj,42.22324041,0.01000,0.631
+10,mlp.down_proj,4.19643478,0.01000,3.880
+11,self_attn.k_proj,2.49720556,0.01000,0.604
+11,self_attn.v_proj,0.84860099,0.01000,0.604
+11,self_attn.q_proj,10.59318743,0.01000,0.614
+11,self_attn.o_proj,1.44926018,0.01000,0.613
+11,mlp.up_proj,34.05972397,0.01000,0.600
+11,mlp.gate_proj,34.98881461,0.01000,0.621
+11,mlp.down_proj,3.78504640,0.01000,3.701
+12,self_attn.k_proj,2.51501925,0.01000,0.643
+12,self_attn.v_proj,1.06571939,0.01000,0.612
+12,self_attn.q_proj,11.37260368,0.01000,0.595
+12,self_attn.o_proj,1.42345318,0.01000,0.574
+12,mlp.up_proj,33.02424516,0.01000,0.609
+12,mlp.gate_proj,32.15129480,0.01000,0.631
+12,mlp.down_proj,4.32310599,0.01000,3.762
+13,self_attn.k_proj,2.17874396,0.01000,0.600
+13,self_attn.v_proj,1.34991701,0.01000,0.585
+13,self_attn.q_proj,11.63673653,0.01000,0.595
+13,self_attn.o_proj,2.12498794,0.01000,0.577
+13,mlp.up_proj,31.13961415,0.01000,0.606
+13,mlp.gate_proj,32.60532906,0.01000,0.599
+13,mlp.down_proj,3.95873230,0.01000,3.753
+14,self_attn.k_proj,2.99430476,0.01000,0.563
+14,self_attn.v_proj,1.20193668,0.01000,0.557
+14,self_attn.q_proj,15.81873781,0.01000,0.563
+14,self_attn.o_proj,2.06551350,0.01000,0.634
+14,mlp.up_proj,33.95725983,0.01000,0.578
+14,mlp.gate_proj,33.69845680,0.01000,0.593
+14,mlp.down_proj,4.71709626,0.01000,3.694
+15,self_attn.k_proj,2.77116690,0.01000,0.609
+15,self_attn.v_proj,1.10220412,0.01000,0.591
+15,self_attn.q_proj,12.72785654,0.01000,0.599
+15,self_attn.o_proj,1.87682963,0.01000,0.609
+15,mlp.up_proj,31.97431222,0.01000,0.659
+15,mlp.gate_proj,30.82866852,0.01000,0.627
+15,mlp.down_proj,4.68322897,0.01000,3.653
+16,self_attn.k_proj,2.65178245,0.01000,0.597
+16,self_attn.v_proj,1.33414724,0.01000,0.595
+16,self_attn.q_proj,13.40043761,0.01000,0.587
+16,self_attn.o_proj,2.56995311,0.01000,0.605
+16,mlp.up_proj,34.49688110,0.01000,0.593
+16,mlp.gate_proj,33.07141986,0.01000,0.594
+16,mlp.down_proj,4.67668955,0.01000,3.801
+17,self_attn.k_proj,2.56790221,0.01000,0.573
+17,self_attn.v_proj,1.63155973,0.01000,0.569
+17,self_attn.q_proj,14.37411106,0.01000,0.567
+17,self_attn.o_proj,2.11580409,0.01000,0.613
+17,mlp.up_proj,40.19091352,0.01000,0.624
+17,mlp.gate_proj,37.72127967,0.01000,0.617
+17,mlp.down_proj,6.41667661,0.01000,3.904
+18,self_attn.k_proj,2.01086315,0.01000,0.627
+18,self_attn.v_proj,1.82605520,0.01000,0.622
+18,self_attn.q_proj,12.26445795,0.01000,0.628
+18,self_attn.o_proj,2.60375627,0.01000,0.626
+18,mlp.up_proj,42.72995571,0.01000,0.637
+18,mlp.gate_proj,39.51592978,0.01000,0.633
+18,mlp.down_proj,7.30472941,0.01000,3.770
+19,self_attn.k_proj,2.03734621,0.01000,0.609
+19,self_attn.v_proj,2.17895159,0.01000,0.608
+19,self_attn.q_proj,13.97130506,0.01000,0.602
+19,self_attn.o_proj,2.98630336,0.01000,0.589
+19,mlp.up_proj,45.40066239,0.01000,0.608
+19,mlp.gate_proj,43.89151394,0.01000,0.612
+19,mlp.down_proj,7.82231198,0.01000,3.688
+20,self_attn.k_proj,2.03618901,0.01000,0.600
+20,self_attn.v_proj,2.32651697,0.01000,0.609
+20,self_attn.q_proj,12.49319835,0.01000,0.644
+20,self_attn.o_proj,2.02054115,0.01000,0.607
+20,mlp.up_proj,53.92699021,0.01000,0.606
+20,mlp.gate_proj,51.74172017,0.01000,0.599
+20,mlp.down_proj,14.09048887,0.01000,3.809
+21,self_attn.k_proj,2.22723000,0.01000,0.632
+21,self_attn.v_proj,3.41219732,0.01000,0.620
+21,self_attn.q_proj,14.44116497,0.01000,0.618
+21,self_attn.o_proj,4.64260670,0.01000,0.616
+21,mlp.up_proj,64.68185143,0.01000,0.632
+21,mlp.gate_proj,65.52687134,0.01000,0.628
+21,mlp.down_proj,17.97917598,0.01000,3.809
+22,self_attn.k_proj,2.89653644,0.01000,0.588
+22,self_attn.v_proj,5.82066236,0.01000,0.582
+22,self_attn.q_proj,18.60508524,0.01000,0.594
+22,self_attn.o_proj,5.02134183,0.01000,0.634
+22,mlp.up_proj,90.02371180,0.01000,0.611
+22,mlp.gate_proj,91.14663930,0.01000,0.615
+22,mlp.down_proj,34.05776069,0.01000,3.731
+23,self_attn.k_proj,4.18426553,0.01000,0.582
+23,self_attn.v_proj,10.33130930,0.01000,0.578
+23,self_attn.q_proj,25.64362199,0.01000,0.571
+23,self_attn.o_proj,13.37783952,0.01000,0.588
+23,mlp.up_proj,125.68233908,0.01000,0.604
+23,mlp.gate_proj,128.76723017,0.01000,0.603
+23,mlp.down_proj,43.81595416,0.01000,3.752
+24,self_attn.k_proj,3.36082683,0.01000,0.582
+24,self_attn.v_proj,10.30109492,0.01000,0.590
+24,self_attn.q_proj,23.33862463,0.01000,0.593
+24,self_attn.o_proj,5.05974270,0.01000,0.585
+24,mlp.up_proj,139.16557624,0.01000,0.603
+24,mlp.gate_proj,132.34724480,0.01000,0.586
+24,mlp.down_proj,59.95090011,0.01000,3.698
+25,self_attn.k_proj,4.10498364,0.01000,0.576
+25,self_attn.v_proj,17.18356073,0.01000,0.562
+25,self_attn.q_proj,27.32380730,0.01000,0.571
+25,self_attn.o_proj,9.62589656,0.01000,0.578
+25,mlp.up_proj,171.75121912,0.01000,0.598
+25,mlp.gate_proj,154.04677341,0.01000,0.583
+25,mlp.down_proj,83.74196908,0.01000,3.576
+26,self_attn.k_proj,5.83665500,0.01000,0.589
+26,self_attn.v_proj,42.81872257,0.01000,0.590
+26,self_attn.q_proj,46.47709586,0.01000,0.595
+26,self_attn.o_proj,23.30883757,0.01000,0.583
+26,mlp.up_proj,170.47679616,0.01000,0.612
+26,mlp.gate_proj,150.27404706,0.01000,0.595
+26,mlp.down_proj,0.00017362,0.01250,4.201
+27,self_attn.k_proj,6.51690253,0.01000,0.592
+27,self_attn.v_proj,61.79766743,0.01000,0.568
+27,self_attn.q_proj,64.76963792,0.01000,0.587
+27,self_attn.o_proj,43.01269404,0.01000,0.577
+27,mlp.up_proj,221.63391986,0.01000,0.607
+27,mlp.gate_proj,214.62520319,0.01000,0.615
+27,mlp.down_proj,415.36760403,0.01000,3.916

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
-size 11422063
+oid sha256:ba0c439f7be467bf47d12a7e6f9adc6116201056fc60c67f431c679b7c16afc8
+size 11422064

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "_commit_hash": null,
   "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
@@ -195,16 +196,15 @@
     "<|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 -%}",
+  "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            {%- for content in message['content'] -%}\n                {%- if content is string -%}\n                    {{- content | trim -}}\n                {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' -%}\n                    {{- image_placeholder | 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,
+  "max_pixels": 23000000,
   "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",