Integrate dit config

config.json

@@ -1,14 +1,68 @@
 {
+  "_name_or_path": "manu/lilt-camembert-dit-base-hf-latest",
   "architectures": [
     "CamembertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "beit_config_dict": {
+    "architectures": [
+      "BeitForMaskedImageModeling"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "auxiliary_channels": 256,
+    "auxiliary_concat_input": false,
+    "auxiliary_loss_weight": 0.4,
+    "auxiliary_num_convs": 1,
+    "drop_path_rate": 0.1,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-12,
+    "layer_scale_init_value": 0.1,
+    "model_type": "beit",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "out_indices": [
+      3,
+      5,
+      7,
+      11
+    ],
+    "patch_size": 16,
+    "pool_scales": [
+      1,
+      2,
+      3,
+      6
+    ],
+    "semantic_loss_ignore_index": 255,
+    "torch_dtype": "float32",
+    "transformers_version": "4.18.0.dev0",
+    "use_absolute_position_embeddings": true,
+    "use_auxiliary_head": true,
+    "use_mask_token": true,
+    "use_mean_pooling": true,
+    "use_relative_position_bias": false,
+    "use_shared_relative_position_bias": false,
+    "vocab_size": 8192
+  },
   "bos_token_id": 5,
   "channel_shrink_ratio": 4,
+  "classifier_dropout": null,
   "eos_token_id": 6,
+  "has_visual_segment_embedding": true,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
+  "image_feature_pool_shape": [
+    14,
+    14,
+    768
+  ],
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
@@ -19,6 +73,9 @@
   "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.17.0",
   "type_vocab_size": 1,
+  "use_cache": true,
   "vocab_size": 32005
-}
+}