Add files using upload-large-folder tool

.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

README.md

@@ -0,0 +1,5 @@
+---
+license: apache-2.0
+library_name: transformers
+---
+# JGOS-398B-VID

config.json

@@ -0,0 +1,171 @@
+{
+  "architectures": [
+    "Qwen3_5MoeForConditionalGeneration"
+  ],
+  "image_token_id": 248056,
+  "model_type": "qwen3_5_moe",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 64,
+    "linear_value_head_dim": 128,
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_moe_text",
+    "moe_intermediate_size": 1024,
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 32,
+    "num_experts": 512,
+    "num_experts_per_tok": 10,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "router_aux_loss_coef": 0.001,
+    "shared_expert_intermediate_size": 1024,
+    "use_cache": true,
+    "vocab_size": 248320,
+    "mamba_ssm_dtype": "float32",
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "rope_type": "default",
+      "rope_theta": 10000000,
+      "partial_rotary_factor": 0.25
+    }
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_moe",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "quantization_config": {
+    "quant_method": "compressed-tensors",
+    "format": "float-quantized",
+    "config_groups": {
+      "group_0": {
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "num_bits": 8,
+          "type": "float",
+          "strategy": "channel",
+          "symmetric": true,
+          "dynamic": false
+        },
+        "input_activations": {
+          "num_bits": 8,
+          "type": "float",
+          "strategy": "token",
+          "symmetric": true,
+          "dynamic": true
+        }
+      }
+    },
+    "ignore": [
+      "lm_head",
+      "re:.*linear_attn.*",
+      "re:.*mlp\\.gate$",
+      "re:.*shared_expert_gate.*",
+      "re:.*norm.*",
+      "re:.*embed_tokens.*",
+      "re:.*visual.*",
+      "re:.*\\.q_norm.*",
+      "re:.*\\.k_norm.*"
+    ]
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 0.6,
+    "top_k": 20,
+    "top_p": 0.95,
+    "transformers_version": "4.57.0.dev0"
+}

model.safetensors-00037-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae4d86c40c2f4e100e04f2862254fbd983ac616ac4b5f76100c5058a64b9449
+size 4299161912

model.safetensors-00038-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561f2714a2a6b7be320a23b1a246003c820f61cf5e9deb058eb9d4595dedc539
+size 4299161912

model.safetensors-00039-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf50b5017bd879004a2732888233345a0246029a9a639a9da8520cb962295239
+size 4299161912

model.safetensors-00040-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c58d3203bf600d5fb2c864d8ca0f18f53897d701b6dc2f6df9bc0328c68c206
+size 4299161912

model.safetensors-00043-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6b1ff5226f4a878bcebdf119bfb61b09880b407bfe5b39521a0405381839a4
+size 4299161912

model.safetensors-00044-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ee63cfcbaa3da49424239b938ccf29cb1e6460071795a2541450f023abb748
+size 4299161912

model.safetensors-00045-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec35d67008b60cd218905e3644d93126c427697ade7d5d502a94ab9d985ec1f
+size 4299161904

model.safetensors-00046-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ab1796a67956cea06cf4e648956354c945be6eaf86ce6d7b4f1b34be99b546
+size 4299161912

model.safetensors-00047-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82575961a353a94c5f7603065cbdacf4c10ab3ef5e6b5d89dc69b451068cc760
+size 4299161912

model.safetensors-00048-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0cd84f5cfdba7b03aa1d32267e2329ff8f6ca755bf751ed14714d0d3f5ca099
+size 4299161912

model.safetensors-00049-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5443df6b1729e3a3c394577b43b9054ec5ba0fb331864c20e44aa822f7b990d3
+size 4299161912

model.safetensors-00050-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988d4fd007dbe1287ed3a6f3df045d181ffaf11067dd4553afe9c62eb57e2ea8
+size 4299161912

model.safetensors-00051-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b545e3a5fa1d23b0586e330dedc251c619c299df3fe7722a7b465abea26f6b8c
+size 4299161912

model.safetensors-00052-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b71bc0f009b7ba95c99bad6bcb1c65eb5c88a0c7e3ee8f096df40b451299f4b
+size 4299161912

model.safetensors-00053-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e99af0cdad48b2ed03293fff380f4bcca3816c95a90dacf916a38678234e6b
+size 4299161912

model.safetensors-00054-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace8607a148ff203dcdd811de62dd32618b8c1764083aded0d02173751b2c11b
+size 4299161912

model.safetensors-00055-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f97ea580efc65ed4430ca8c3d73c37c7916773d03a37aa9bc39adea0de4548
+size 4299161912

model.safetensors-00056-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337e10c33113ae54eb573324269d0f4d91bf7ac5bf0d370fe38d1c797b6549a3
+size 4299161912

model.safetensors-00057-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d995b4b39f0f27a7bc4adb98049d562e7e4c67f3350234863f792b39350fd41
+size 4299161912

model.safetensors-00058-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da028c7d45cf5d641eed6b099dc0255cac448b5ddb3c8b0b6995902156d60c7
+size 4299161912

model.safetensors-00061-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b37263dc5e29f490b4830e4166644ec85feb56d11f225aeef71e0fdba6d942a
+size 4311745088

model.safetensors-00064-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6558f0c50cddb2357f775b0af2be426df3dfa225b01345caf3e46930041ad766
+size 4311745088

model.safetensors-00065-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c37d1c6f4d936b25e9cceb41bd2bbdd526b54a2d428200f0280fa23b6f75599
+size 4311745088

model.safetensors-00066-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5314be0b6b4d1a9165105e4ae4796dae7e02b1fd78b73ba5ba28e005f7dc7a11
+size 4311745088

model.safetensors-00067-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0655917274b851b0d4c6ba1d61357a39433a656fed9d96fac4e5fbcfd00ee2
+size 4311745088

model.safetensors-00070-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b532d3ceb129d3affb39ca15bd40ca03b2c284ca89dc8fb93f0dd9a525f4ba
+size 4311745088

model.safetensors-00071-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584f3755d8226ccd227f89a48b10d1867a8ecc97ceb99c752afc37378c6a564d
+size 4311745088

model.safetensors-00075-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff51f5dc1035f2652dd1bb0955494cc78afd2d1a13e0b2929c3168d27b460010
+size 4311745088

model.safetensors-00077-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb1ab4d641491f6a24b1feec48a57e72715c7006fbae5d045796401444a1549
+size 4311745088

model.safetensors-00078-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3692f10448cff7d229355d035ede1177009509b0233b9c22aa3f0338c52c4296
+size 4311745088

model.safetensors-00080-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ca3e591cebcb9847224ea47654a63b4eb50008aeb1ac823c2ed70f69199448
+size 4311745088

model.safetensors-00081-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f104a5b5a5973bec6ea67b2cbf64b6248de6cb3bcfa5bbf9bc90d63eaa6a3c2f
+size 4311745088

model.safetensors-00082-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3b34983ce6daae679df519ff5004edc582ac144777edae2d172f1f7f997ac5
+size 4311745088

model.safetensors-00084-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f34a30cb4e654396ea4f069a674ee4edcee96a1a285b58ede5165fc2b39eca
+size 4311745088

model.safetensors-00085-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328d84444a68cbb854863aca224d21c2ada211607f279460df0a00f415a83fb8
+size 4311745088

model.safetensors-00087-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e49b4013129cd7da8a52ab553b3045a5d99e7f2b5be95aeb92cdbb312f57fb4
+size 4311745088

model.safetensors-00088-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f76aec810f0718996407afd6575eee492a00c90744de6621af4090384ae1eb
+size 4311745088

model.safetensors-00090-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7caea2705a367a2d7a74c48393a0cbf8bb96377ffbcd8d994a2f352672e8ce6
+size 4311745088

model.safetensors-00091-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b367d427d788fcab2d56a62a9f3c93164cb4df78fb72575a308527a24bba751e
+size 8632869792

model.safetensors-00094-of-00094.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d26f47e9ef06271f3a448cf49bce606ae7e399e89e4a8660b5c8b2ffd3ee5f
+size 4000125000

preprocessor_config.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
+size 12807982

tokenizer_config.json

@@ -0,0 +1,305 @@
+{
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+        "248044": {
+            "content": "<|endoftext|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248045": {
+            "content": "<|im_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248046": {
+            "content": "<|im_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248047": {
+            "content": "<|object_ref_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248048": {
+            "content": "<|object_ref_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248049": {
+            "content": "<|box_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248050": {
+            "content": "<|box_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248051": {
+            "content": "<|quad_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248052": {
+            "content": "<|quad_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248053": {
+            "content": "<|vision_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248054": {
+            "content": "<|vision_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248055": {
+            "content": "<|vision_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248056": {
+            "content": "<|image_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248057": {
+            "content": "<|video_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248058": {
+            "content": "<tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248059": {
+            "content": "</tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248060": {
+            "content": "<|fim_prefix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248061": {
+            "content": "<|fim_middle|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248062": {
+            "content": "<|fim_suffix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248063": {
+            "content": "<|fim_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248064": {
+            "content": "<|repo_name|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248065": {
+            "content": "<|file_sep|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248066": {
+            "content": "<tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248067": {
+            "content": "</tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248068": {
+            "content": "<think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248069": {
+            "content": "</think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248070": {
+            "content": "<|audio_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248071": {
+            "content": "<|audio_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248072": {
+            "content": "<tts_pad>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248073": {
+            "content": "<tts_text_bos>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248074": {
+            "content": "<tts_text_eod>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248075": {
+            "content": "<tts_text_bos_single>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248076": {
+            "content": "<|audio_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "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) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|im_end|>",
+    "errors": "replace",
+    "model_max_length": 262144,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false,
+    "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+    "extra_special_tokens": {
+        "audio_bos_token": "<|audio_start|>",
+        "audio_eos_token": "<|audio_end|>",
+        "audio_token": "<|audio_pad|>",
+        "image_token": "<|image_pad|>",
+        "video_token": "<|video_pad|>",
+        "vision_bos_token": "<|vision_start|>",
+        "vision_eos_token": "<|vision_end|>"
+    }
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}