Update config.json

config.json

@@ -2,34 +2,30 @@
   "architectures": [
     "Qwen2_5_VLForConditionalGeneration"
   ],
-  "vision_config": {
-    "depth": 32,
-    "hidden_act": "silu",
-    "hidden_size": 1280,
-    "intermediate_size": 3456,
-    "num_heads": 16,
-    "in_chans": 3,
-    "out_hidden_size": 8192,
-    "patch_size": 14,
-    "spatial_merge_size": 2,
-    "spatial_patch_size": 14,
-    "window_size": 112,
-    "fullatt_block_indexes": [
-      7,
-      15,
-      23,
-      31
-    ],
-    "tokens_per_second": 2,
-    "temporal_patch_size": 2
-  },
-  "rope_scaling": {
-    "type": "mrope",
-    "mrope_section": [
-      16,
-      24,
-      24
-    ]
-  },
-  "vocab_size": 152064
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "vision_token_id": 151654,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 80,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
 }