support older transformers versions

config.json

@@ -13,13 +13,13 @@
     "architectures": null,
     "attention_dropout": 0.0,
     "bad_words_ids": null,
-    "begin_suppress_tokens": null,
     "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
     "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
+    "dropout": 0.0,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 2,
@@ -60,14 +60,12 @@
     "pad_token_id": 1,
     "prefix": null,
     "problem_type": null,
-    "projection_dim": 512,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
     "sep_token_id": null,
-    "suppress_tokens": null,
     "task_specific_params": null,
     "temperature": 1.0,
     "tf_legacy_loss": false,
@@ -78,11 +76,17 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.30.0.dev0",
+    "transformers_version": "4.23.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
   },
+  "text_config_dict": {
+    "hidden_act": "gelu",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_attention_heads": 12
+  },
   "torch_dtype": "float32",
   "transformers_version": null,
   "vision_config": {
@@ -91,13 +95,13 @@
     "architectures": null,
     "attention_dropout": 0.0,
     "bad_words_ids": null,
-    "begin_suppress_tokens": null,
     "bos_token_id": null,
     "chunk_size_feed_forward": 0,
     "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
+    "dropout": 0.0,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": null,
@@ -140,14 +144,12 @@
     "patch_size": 14,
     "prefix": null,
     "problem_type": null,
-    "projection_dim": 512,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
     "sep_token_id": null,
-    "suppress_tokens": null,
     "task_specific_params": null,
     "temperature": 1.0,
     "tf_legacy_loss": false,
@@ -158,8 +160,16 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.30.0.dev0",
+    "transformers_version": "4.23.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
   }
 }