Update config.json

config.json

@@ -1,86 +1,86 @@
 {
-  "vision_config": {
+  "_name_or_path": "microsoft/Florence-2-base",
+  "architectures": [
+    "Florence2ForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "microsoft/Florence-2-base--configuration_florence2.Florence2Config",
+    "AutoModelForCausalLM": "microsoft/Florence-2-base--modeling_florence2.Florence2ForConditionalGeneration"
+  },
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "ignore_index": -100,
+  "is_encoder_decoder": true,
+  "model_type": "florence2",
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "text_config": {
     "_name_or_path": "",
+    "activation_dropout": 0.1,
+    "activation_function": "gelu",
+    "add_bias_logits": false,
     "add_cross_attention": false,
-    "architectures": null,
+    "add_final_layer_norm": false,
+    "attention_dropout": 0.1,
     "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
+    "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
+    "classif_dropout": 0.1,
+    "classifier_dropout": 0.0,
     "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
+    "d_model": 768,
+    "decoder_attention_heads": 12,
+    "decoder_ffn_dim": 3072,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "decoder_start_token_id": 2,
+    "dropout": 0.1,
+    "encoder_attention_heads": 12,
+    "encoder_ffn_dim": 3072,
+    "encoder_layers": 6,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 1024,
+    "model_type": "florence2_language",
+    "no_repeat_ngram_size": 3,
+    "num_beam_groups": 1,
+    "num_beams": 3,
+    "num_hidden_layers": 6,
+    "pad_token_id": 1,
+    "return_dict": true
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "vision_config": {
+    "add_cross_attention": false,
+    "architectures": null,
     "depths": [1, 1, 9, 1],
     "dim_embed": [128, 256, 512, 1024],
-    "diversity_penalty": 0.0,
-    "do_sample": false,
     "drop_path_rate": 0.1,
-    "early_stopping": false,
-    "enable_checkpoint": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "image_feature_source": ["spatial_avg_pool", "temporal_avg_pool"],
     "image_pos_embed": {
       "max_pos_embeddings": 50,
       "type": "learned_abs_2d"
     },
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "davit",  // <--- Add this line
-    "no_repeat_ngram_size": 0,
-    "num_beam_groups": 1,
-    "num_beams": 1,
+    "model_type": "davit",  // This is the required change
     "num_groups": [4, 8, 16, 32],
     "num_heads": [4, 8, 16, 32],
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
     "patch_padding": [3, 1, 1, 1],
-    "patch_prenorm": [false, true, true, true],
     "patch_size": [7, 3, 3, 3],
     "patch_stride": [4, 2, 2, 2],
-    "prefix": null,
-    "problem_type": null,
     "projection_dim": 768,
-    "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,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
     "visual_temporal_embedding": {
       "max_temporal_embeddings": 100,
       "type": "COSINE"
     },
     "window_size": 12
-  }
+  },
+  "vocab_size": 51289
 }