Update config.json

config.json

@@ -12,7 +12,7 @@
   "ignore_index": -100,
   "model_type": "florence2",
   "pad_token_id": 1,
-  "projection_dim": 768,
+  "projection_dim": 1024,
   "text_config": {
       "vocab_size": 51289,
       "activation_dropout": 0.1,
@@ -23,18 +23,18 @@
       "bos_token_id": 0,
       "classif_dropout": 0.1,
       "classifier_dropout": 0.0,
-      "d_model": 768,
-      "decoder_attention_heads": 12,
-      "decoder_ffn_dim": 3072,
+      "d_model": 1024,
+      "decoder_attention_heads": 16,
+      "decoder_ffn_dim": 4096,
       "decoder_layerdrop": 0.0,
-      "decoder_layers": 6,
+      "decoder_layers": 12,
       "decoder_start_token_id": 2,
       "dropout": 0.1,
       "early_stopping": true,
-      "encoder_attention_heads": 12,
-      "encoder_ffn_dim": 3072,
+      "encoder_attention_heads": 16,
+      "encoder_ffn_dim": 4096,
       "encoder_layerdrop": 0.0,
-      "encoder_layers": 6,
+      "encoder_layers": 12,
       "eos_token_id": 2,
       "forced_eos_token_id": 2,
       "forced_bos_token_id": 0,
@@ -49,7 +49,7 @@
       "max_position_embeddings": 1024,
       "no_repeat_ngram_size": 3,
       "normalize_before": false,
-      "num_hidden_layers": 6,
+      "num_hidden_layers": 12,
       "pad_token_id": 1,
       "scale_embedding": false,
       "num_beams": 3
@@ -62,12 +62,12 @@
     "patch_padding": [3, 1, 1, 1],  
     "patch_prenorm": [false, true, true, true],  
     "enable_checkpoint": false,  
-    "dim_embed": [128, 256, 512, 1024],
-    "num_heads": [4, 8, 16, 32],
-    "num_groups": [4, 8, 16, 32],
+    "dim_embed": [256, 512, 1024, 2048],  
+    "num_heads": [8, 16, 32, 64],  
+    "num_groups": [8, 16, 32, 64],  
     "depths": [1, 1, 9, 1],  
     "window_size": 12,
-    "projection_dim": 768,
+    "projection_dim": 1024,
     "visual_temporal_embedding": {
         "type": "COSINE",
         "max_temporal_embeddings": 100