Upload Qwen2_5_VLForConditionalGeneration

config.json

@@ -2,42 +2,12 @@
   "architectures": [
     "Qwen2_5_VLForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
   "dtype": "bfloat16",
-  "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,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": {
-    "mrope_section": [
-      16,
-      24,
-      24
-    ],
-    "rope_type": "default",
-    "type": "default"
-  },
-  "rope_theta": 1000000.0,
-  "sliding_window": 32768,
   "text_config": {
-    "_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
-    "architectures": [
-      "Qwen2_5_VLForConditionalGeneration"
-    ],
     "attention_dropout": 0.0,
-    "bos_token_id": 151643,
     "dtype": "bfloat16",
-    "eos_token_id": 151645,
     "hidden_act": "silu",
     "hidden_size": 16,
     "initializer_range": 0.02,
@@ -53,25 +23,23 @@
     "num_hidden_layers": 2,
     "num_key_value_heads": 2,
     "rms_norm_eps": 1e-06,
-    "rope_scaling": {
+    "rope_parameters": {
       "mrope_section": [
         1,
         1
       ],
+      "rope_theta": 1000000.0,
       "rope_type": "default",
       "type": "default"
     },
-    "rope_theta": 1000000.0,
     "sliding_window": null,
     "tie_word_embeddings": true,
     "use_cache": true,
     "use_sliding_window": false,
-    "vision_token_id": 151654,
     "vocab_size": 151936
   },
-  "transformers_version": "4.57.1",
-  "use_cache": true,
-  "use_sliding_window": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0.dev0",
   "video_token_id": 151656,
   "vision_config": {
     "depth": 32,
@@ -103,6 +71,5 @@
   },
   "vision_end_token_id": 151653,
   "vision_start_token_id": 151652,
-  "vision_token_id": 151654,
-  "vocab_size": 151936
+  "vision_token_id": 151654
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
-  "transformers_version": "4.57.1"
+  "transformers_version": "5.0.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ee6de012cbabb328744133306ae85256f9d1d994145c50a0a341918c7af35c
+oid sha256:0d65a042afb5cad045b9e8d426c926dec7e479d4f11453cd6ce30779074c0097
 size 18086192

processor_config.json

@@ -0,0 +1,87 @@
+{
+  "image_processor": {
+    "crop_size": null,
+    "data_format": "channels_first",
+    "device": null,
+    "disable_grouping": null,
+    "do_center_crop": null,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_pad": null,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_seq_length": null,
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "input_data_format": null,
+    "max_pixels": 12845056,
+    "merge_size": 2,
+    "min_pixels": 3136,
+    "pad_size": null,
+    "patch_size": 14,
+    "processor_class": "Qwen2_5_VLProcessor",
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_tensors": null,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "crop_size": null,
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "device": null,
+    "do_center_crop": null,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_pad": null,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "fps": null,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "input_data_format": null,
+    "max_frames": 768,
+    "max_pixels": 12845056,
+    "merge_size": 2,
+    "min_frames": 4,
+    "min_pixels": 3136,
+    "num_frames": null,
+    "pad_size": null,
+    "patch_size": 14,
+    "processor_class": "Qwen2_5_VLProcessor",
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "return_tensors": null,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_metadata": null,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

tokenizer_config.json

@@ -1,185 +1,13 @@
 {
   "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": [
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
     "<|im_start|>",
     "<|im_end|>",
     "<|object_ref_start|>",
@@ -194,11 +22,7 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
+  "is_local": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "processor_class": "Qwen2_5_VLProcessor",