Upload 14 files

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "microsoft/Florence-2-base",
+  "_name_or_path": "MiaoshouAI/Florence-2-base-PromptGen-v2.0",
   "architectures": [
     "Florence2ForConditionalGeneration"
   ],
   "auto_map": {
-    "AutoConfig": "configuration_florence2.Florence2Config",
-    "AutoModelForCausalLM": "modeling_florence2.Florence2ForConditionalGeneration"
+    "AutoConfig": "MiaoshouAI/Florence-2-base-PromptGen-v2.0--configuration_florence2.Florence2Config",
+    "AutoModelForCausalLM": "MiaoshouAI/Florence-2-base-PromptGen-v2.0--modeling_florence2.Florence2ForConditionalGeneration"
   },
   "bos_token_id": 0,
   "eos_token_id": 2,
@@ -104,34 +104,134 @@
     "use_cache": true,
     "vocab_size": 51289
   },
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
   "vision_config": {
-    "model_type": "davit",
-    "drop_path_rate": 0.1,  
-    "patch_size": [7, 3, 3, 3],  
-    "patch_stride": [4, 2, 2, 2],  
-    "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],
-    "depths": [1, 1, 9, 1],  
-    "window_size": 12,
-    "projection_dim": 768,
-    "visual_temporal_embedding": {
-        "type": "COSINE",
-        "max_temporal_embeddings": 100
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "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,
+    "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": {
-        "type": "learned_abs_2d",
-        "max_pos_embeddings": 50
+      "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": "",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "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"
     },
-    "image_feature_source": ["spatial_avg_pool", "temporal_avg_pool"]
+    "window_size": 12
   },
-  "vocab_size": 51289,
-  "torch_dtype": "float16",
-  "transformers_version": "4.41.0.dev0",
-  "is_encoder_decoder": true
+  "vocab_size": 51289
 }

onnx/decoder_model_merged.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86400f82da6b7891b1ee961057d924399c460987147eb15a558d913622fc0606
-size 388227410
+oid sha256:ae87e04b1a7888db5383496925c4011b60b2660a85872c3c954d49d809edabc9
+size 388227338

onnx/decoder_with_past_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8d6e6959160a960f9498c87d848ab048d60c8b2d9096b04de3cd353e827355
-size 359632410
+oid sha256:63d8d387922e66226baa640d82762a102767df436bee08f1409b3c307403e765
+size 359634870

preprocessor_config.json

@@ -1,6 +1,23 @@
 {
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
   "auto_map": {
-    "AutoProcessor": "processing_florence2.Florence2Processor"
+    "AutoProcessor": "MiaoshouAI/Florence-2-base-PromptGen-v2.0--processing_florence2.Florence2Processor"
   },
   "crop_size": {
     "height": 768,