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_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|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": 2048,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "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": true,
+  "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": 2048,
+    "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": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "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.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1894b51f41c28a63334dc4425bc23b78b256554503c2f60c9dbbc63b6c26a544
+size 3405167488

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": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

quant_log.csv

@@ -0,0 +1,253 @@
+layer,module,loss,samples,damp,time
+0,self_attn.k_proj,0.74444008,0.01000,0.885
+0,self_attn.v_proj,0.10742732,0.01000,0.356
+0,self_attn.q_proj,3.48395300,0.01000,0.357
+0,self_attn.o_proj,0.35185614,0.01000,0.356
+0,mlp.up_proj,2.17084384,0.01000,0.367
+0,mlp.gate_proj,2.70702529,0.01000,0.356
+0,mlp.down_proj,20861.74218750,0.01250,2.234
+1,self_attn.k_proj,0.13084082,0.01000,0.362
+1,self_attn.v_proj,0.02736288,0.01000,0.362
+1,self_attn.q_proj,0.49381298,0.01000,0.352
+1,self_attn.o_proj,0.21891856,0.01000,0.349
+1,mlp.up_proj,727.67602539,0.01000,0.351
+1,mlp.gate_proj,1028.54296875,0.01000,0.354
+1,mlp.down_proj,9785.07421875,0.01250,2.221
+2,self_attn.k_proj,0.13992883,0.01000,0.370
+2,self_attn.v_proj,0.03649667,0.01000,0.362
+2,self_attn.q_proj,0.63483173,0.01000,0.364
+2,self_attn.o_proj,0.12606674,0.01000,0.372
+2,mlp.up_proj,193.19320679,0.01000,0.375
+2,mlp.gate_proj,143.89367676,0.01000,0.366
+2,mlp.down_proj,4596.45605469,0.01000,2.030
+3,self_attn.k_proj,0.51369303,0.01000,0.356
+3,self_attn.v_proj,0.11681624,0.01000,0.355
+3,self_attn.q_proj,2.41911650,0.01000,0.361
+3,self_attn.o_proj,0.07069188,0.01000,0.352
+3,mlp.up_proj,145.86698914,0.01000,0.357
+3,mlp.gate_proj,137.20137024,0.01000,0.363
+3,mlp.down_proj,11.82832718,0.01000,2.040
+4,self_attn.k_proj,0.40270334,0.01000,0.359
+4,self_attn.v_proj,0.15191284,0.01000,0.360
+4,self_attn.q_proj,2.17439270,0.01000,0.358
+4,self_attn.o_proj,0.10469086,0.01000,0.358
+4,mlp.up_proj,107.06092834,0.01000,0.357
+4,mlp.gate_proj,126.43922424,0.01000,0.356
+4,mlp.down_proj,3052.57812500,0.01250,2.163
+5,self_attn.k_proj,0.63042736,0.01000,0.357
+5,self_attn.v_proj,0.30033636,0.01000,0.354
+5,self_attn.q_proj,3.54086185,0.01000,0.358
+5,self_attn.o_proj,0.09380557,0.01000,0.350
+5,mlp.up_proj,185.13006592,0.01000,0.361
+5,mlp.gate_proj,206.14726257,0.01000,0.364
+5,mlp.down_proj,21478.90234375,0.01250,2.125
+6,self_attn.k_proj,0.50094360,0.01000,0.353
+6,self_attn.v_proj,0.26197341,0.01000,0.353
+6,self_attn.q_proj,3.01855040,0.01000,0.359
+6,self_attn.o_proj,0.33328652,0.01000,0.356
+6,mlp.up_proj,192.00917053,0.01000,0.356
+6,mlp.gate_proj,220.45602417,0.01000,0.354
+6,mlp.down_proj,23218.81640625,0.01250,2.132
+7,self_attn.k_proj,0.49787536,0.01000,0.358
+7,self_attn.v_proj,0.33573246,0.01000,0.351
+7,self_attn.q_proj,3.41708875,0.01000,0.350
+7,self_attn.o_proj,0.17219532,0.01000,0.353
+7,mlp.up_proj,129.18815613,0.01000,0.356
+7,mlp.gate_proj,146.09684753,0.01000,0.350
+7,mlp.down_proj,7180.02050781,0.01250,2.146
+8,self_attn.k_proj,0.58210206,0.01000,0.355
+8,self_attn.v_proj,0.41059220,0.01000,0.345
+8,self_attn.q_proj,3.74338007,0.01000,0.346
+8,self_attn.o_proj,0.26617277,0.01000,0.347
+8,mlp.up_proj,118.61260986,0.01000,0.346
+8,mlp.gate_proj,157.80934143,0.01000,0.351
+8,mlp.down_proj,12263.30273438,0.01250,2.119
+9,self_attn.k_proj,0.62588191,0.01000,0.353
+9,self_attn.v_proj,0.37748742,0.01000,0.355
+9,self_attn.q_proj,3.45860744,0.01000,0.353
+9,self_attn.o_proj,0.22479211,0.01000,0.352
+9,mlp.up_proj,93.18229675,0.01000,0.349
+9,mlp.gate_proj,131.35951233,0.01000,0.346
+9,mlp.down_proj,8569.00585938,0.01250,2.159
+10,self_attn.k_proj,0.60444546,0.01000,0.359
+10,self_attn.v_proj,0.51454628,0.01000,0.365
+10,self_attn.q_proj,4.18705559,0.01000,0.368
+10,self_attn.o_proj,0.28868338,0.01000,0.376
+10,mlp.up_proj,55.67261124,0.01000,0.389
+10,mlp.gate_proj,81.45370483,0.01000,0.377
+10,mlp.down_proj,7921.27148438,0.01250,2.115
+11,self_attn.k_proj,0.51484716,0.01000,0.371
+11,self_attn.v_proj,0.42126417,0.01000,0.356
+11,self_attn.q_proj,3.25378394,0.01000,0.355
+11,self_attn.o_proj,0.38483173,0.01000,0.351
+11,mlp.up_proj,19.80066681,0.01000,0.351
+11,mlp.gate_proj,26.65781403,0.01000,0.348
+11,mlp.down_proj,5129.86328125,0.01250,2.207
+12,self_attn.k_proj,0.58728415,0.01000,0.379
+12,self_attn.v_proj,0.41301179,0.01000,0.373
+12,self_attn.q_proj,3.63880444,0.01000,0.373
+12,self_attn.o_proj,0.56821018,0.01000,0.371
+12,mlp.up_proj,22.49377060,0.01000,0.373
+12,mlp.gate_proj,31.48363304,0.01000,0.373
+12,mlp.down_proj,7257.49707031,0.01250,2.227
+13,self_attn.k_proj,0.82758236,0.01000,0.372
+13,self_attn.v_proj,0.34952715,0.01000,0.383
+13,self_attn.q_proj,4.68162632,0.01000,0.383
+13,self_attn.o_proj,0.31500027,0.01000,0.381
+13,mlp.up_proj,13.15117073,0.01000,0.381
+13,mlp.gate_proj,13.66710758,0.01000,0.377
+13,mlp.down_proj,9506.42089844,0.01250,2.143
+14,self_attn.k_proj,0.63195586,0.01000,0.359
+14,self_attn.v_proj,0.36958307,0.01000,0.357
+14,self_attn.q_proj,3.79256201,0.01000,0.359
+14,self_attn.o_proj,0.45079222,0.01000,0.358
+14,mlp.up_proj,12.99849415,0.01000,0.348
+14,mlp.gate_proj,13.64067364,0.01000,0.347
+14,mlp.down_proj,8234.67382812,0.01250,2.111
+15,self_attn.k_proj,0.66956985,0.01000,0.352
+15,self_attn.v_proj,0.39820826,0.01000,0.348
+15,self_attn.q_proj,4.09530163,0.01000,0.357
+15,self_attn.o_proj,0.48171890,0.01000,0.360
+15,mlp.up_proj,12.65697289,0.01000,0.363
+15,mlp.gate_proj,12.20823669,0.01000,0.353
+15,mlp.down_proj,9293.73339844,0.01250,2.079
+16,self_attn.k_proj,0.65244371,0.01000,0.347
+16,self_attn.v_proj,0.37970379,0.01000,0.352
+16,self_attn.q_proj,3.80968571,0.01000,0.345
+16,self_attn.o_proj,0.45385969,0.01000,0.340
+16,mlp.up_proj,12.97595787,0.01000,0.343
+16,mlp.gate_proj,13.41720200,0.01000,0.341
+16,mlp.down_proj,7473.39355469,0.01250,2.136
+17,self_attn.k_proj,1.04092526,0.01000,0.354
+17,self_attn.v_proj,0.57335430,0.01000,0.356
+17,self_attn.q_proj,6.12183523,0.01000,0.347
+17,self_attn.o_proj,0.51757109,0.01000,0.344
+17,mlp.up_proj,12.56683350,0.01000,0.345
+17,mlp.gate_proj,12.42699528,0.01000,0.346
+17,mlp.down_proj,8867.97656250,0.01250,2.191
+18,self_attn.k_proj,0.70069391,0.01000,0.353
+18,self_attn.v_proj,0.43670875,0.01000,0.345
+18,self_attn.q_proj,4.41953039,0.01000,0.345
+18,self_attn.o_proj,0.44703659,0.01000,0.342
+18,mlp.up_proj,12.66960430,0.01000,0.352
+18,mlp.gate_proj,13.09418678,0.01000,0.351
+18,mlp.down_proj,9041.26171875,0.01250,2.156
+19,self_attn.k_proj,0.97574604,0.01000,0.360
+19,self_attn.v_proj,0.45846105,0.01000,0.353
+19,self_attn.q_proj,5.56507254,0.01000,0.351
+19,self_attn.o_proj,0.68781030,0.01000,0.349
+19,mlp.up_proj,12.41621017,0.01000,0.351
+19,mlp.gate_proj,12.02220726,0.01000,0.344
+19,mlp.down_proj,10349.19628906,0.01250,2.095
+20,self_attn.k_proj,0.91374326,0.01000,0.361
+20,self_attn.v_proj,0.84225118,0.01000,0.352
+20,self_attn.q_proj,7.90642452,0.01000,0.353
+20,self_attn.o_proj,0.65266848,0.01000,0.348
+20,mlp.up_proj,13.25346375,0.01000,0.350
+20,mlp.gate_proj,13.00006485,0.01000,0.345
+20,mlp.down_proj,10541.17480469,0.01250,2.112
+21,self_attn.k_proj,0.91980761,0.01000,0.348
+21,self_attn.v_proj,0.60435474,0.01000,0.352
+21,self_attn.q_proj,5.79789162,0.01000,0.354
+21,self_attn.o_proj,0.47814932,0.01000,0.349
+21,mlp.up_proj,12.88965511,0.01000,0.339
+21,mlp.gate_proj,13.68577003,0.01000,0.349
+21,mlp.down_proj,9139.45312500,0.01250,2.127
+22,self_attn.k_proj,1.08109522,0.01000,0.347
+22,self_attn.v_proj,0.92851174,0.01000,0.339
+22,self_attn.q_proj,7.33548689,0.01000,0.345
+22,self_attn.o_proj,0.52778512,0.01000,0.355
+22,mlp.up_proj,13.11236668,0.01000,0.351
+22,mlp.gate_proj,13.37494373,0.01000,0.343
+22,mlp.down_proj,8655.26269531,0.01250,2.088
+23,self_attn.k_proj,1.04391277,0.01000,0.344
+23,self_attn.v_proj,0.51679677,0.01000,0.342
+23,self_attn.q_proj,6.92970991,0.01000,0.344
+23,self_attn.o_proj,0.67145306,0.01000,0.353
+23,mlp.up_proj,13.89229584,0.01000,0.353
+23,mlp.gate_proj,13.28810978,0.01000,0.352
+23,mlp.down_proj,7284.98974609,0.01250,2.126
+24,self_attn.k_proj,0.72494310,0.01000,0.341
+24,self_attn.v_proj,0.60319602,0.01000,0.340
+24,self_attn.q_proj,5.09278584,0.01000,0.343
+24,self_attn.o_proj,0.64103162,0.01000,0.352
+24,mlp.up_proj,14.46055412,0.01000,0.348
+24,mlp.gate_proj,13.96115685,0.01000,0.349
+24,mlp.down_proj,5808.32568359,0.01250,2.098
+25,self_attn.k_proj,0.68927372,0.01000,0.345
+25,self_attn.v_proj,0.90973526,0.01000,0.347
+25,self_attn.q_proj,6.57881737,0.01000,0.341
+25,self_attn.o_proj,0.55416870,0.01000,0.344
+25,mlp.up_proj,15.76302910,0.01000,0.340
+25,mlp.gate_proj,15.58094025,0.01000,0.343
+25,mlp.down_proj,5237.87109375,0.01250,2.123
+26,self_attn.k_proj,0.67382836,0.01000,0.352
+26,self_attn.v_proj,0.86641783,0.01000,0.347
+26,self_attn.q_proj,5.17918015,0.01000,0.349
+26,self_attn.o_proj,0.62282288,0.01000,0.353
+26,mlp.up_proj,18.80608368,0.01000,0.358
+26,mlp.gate_proj,17.79819107,0.01000,0.349
+26,mlp.down_proj,4985.92187500,0.01250,2.078
+27,self_attn.k_proj,0.71032202,0.01000,0.352
+27,self_attn.v_proj,1.20441103,0.01000,0.344
+27,self_attn.q_proj,7.94571781,0.01000,0.347
+27,self_attn.o_proj,1.24723363,0.01000,0.353
+27,mlp.up_proj,19.54417419,0.01000,0.340
+27,mlp.gate_proj,19.26416397,0.01000,0.337
+27,mlp.down_proj,3807.88183594,0.01250,2.088
+28,self_attn.k_proj,0.66512120,0.01000,0.346
+28,self_attn.v_proj,1.11120594,0.01000,0.341
+28,self_attn.q_proj,6.27659225,0.01000,0.341
+28,self_attn.o_proj,1.05752707,0.01000,0.346
+28,mlp.up_proj,21.45988464,0.01000,0.352
+28,mlp.gate_proj,21.38830185,0.01000,0.349
+28,mlp.down_proj,2827.79541016,0.01250,2.116
+29,self_attn.k_proj,0.74089134,0.01000,0.336
+29,self_attn.v_proj,1.03641844,0.01000,0.340
+29,self_attn.q_proj,6.34802437,0.01000,0.338
+29,self_attn.o_proj,0.88373530,0.01000,0.337
+29,mlp.up_proj,25.68251038,0.01000,0.341
+29,mlp.gate_proj,25.25678253,0.01000,0.339
+29,mlp.down_proj,1534.93933105,0.01250,2.130
+30,self_attn.k_proj,0.73889565,0.01000,0.344
+30,self_attn.v_proj,1.66333413,0.01000,0.341
+30,self_attn.q_proj,8.21355247,0.01000,0.340
+30,self_attn.o_proj,2.45891666,0.01000,0.343
+30,mlp.up_proj,44.94103241,0.01000,0.341
+30,mlp.gate_proj,42.21282959,0.01000,0.343
+30,mlp.down_proj,2631.11474609,0.01000,1.957
+31,self_attn.k_proj,0.67966712,0.01000,0.344
+31,self_attn.v_proj,1.11340189,0.01000,0.341
+31,self_attn.q_proj,7.13615417,0.01000,0.338
+31,self_attn.o_proj,4.71965170,0.01000,0.335
+31,mlp.up_proj,36.13351440,0.01000,0.336
+31,mlp.gate_proj,32.18393326,0.01000,0.342
+31,mlp.down_proj,1051.25756836,0.01250,2.055
+32,self_attn.k_proj,0.79060119,0.01000,0.337
+32,self_attn.v_proj,1.96972919,0.01000,0.338
+32,self_attn.q_proj,9.46166706,0.01000,0.344
+32,self_attn.o_proj,10.08163261,0.01000,0.342
+32,mlp.up_proj,39.15551376,0.01000,0.340
+32,mlp.gate_proj,34.83209991,0.01000,0.346
+32,mlp.down_proj,1009.26580811,0.01250,2.056
+33,self_attn.k_proj,0.78602415,0.01000,0.336
+33,self_attn.v_proj,3.98627043,0.01000,0.344
+33,self_attn.q_proj,9.23457336,0.01000,0.340
+33,self_attn.o_proj,18.25443840,0.01000,0.342
+33,mlp.up_proj,41.35702133,0.01000,0.338
+33,mlp.gate_proj,33.30444717,0.01000,0.348
+33,mlp.down_proj,502.54034424,0.01250,2.034
+34,self_attn.k_proj,0.63516819,0.01000,0.348
+34,self_attn.v_proj,2.11687756,0.01000,0.335
+34,self_attn.q_proj,6.63668060,0.01000,0.338
+34,self_attn.o_proj,8.04108810,0.01000,0.336
+34,mlp.up_proj,52.49430084,0.01000,0.346
+34,mlp.gate_proj,44.75306702,0.01000,0.337
+34,mlp.down_proj,385.97592163,0.01250,2.020
+35,self_attn.k_proj,0.63379931,0.01000,0.336
+35,self_attn.v_proj,1.89587736,0.01000,0.340
+35,self_attn.q_proj,6.26210308,0.01000,0.338
+35,self_attn.o_proj,5.39271402,0.01000,0.346
+35,mlp.up_proj,91.85729980,0.01000,0.347
+35,mlp.gate_proj,83.25270081,0.01000,0.338
+35,mlp.down_proj,2031.59887695,0.01000,1.917

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 +1,25 @@
+{
+  "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": "<|vision_pad|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|vision_pad|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2TokenizerFast",
+  "unk_token": null,
+  "_commit_hash": null
+}