Upload Florence2ForConditionalGeneration

config.json

@@ -10,76 +10,228 @@
   "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": {
-      "vocab_size": 51289,
-      "activation_dropout": 0.1,
-      "activation_function": "gelu",
-      "add_bias_logits": false,
-      "add_final_layer_norm": false,
-      "attention_dropout": 0.1,
-      "bos_token_id": 0,
-      "classif_dropout": 0.1,
-      "classifier_dropout": 0.0,
-      "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,
-      "early_stopping": true,
-      "encoder_attention_heads": 12,
-      "encoder_ffn_dim": 3072,
-      "encoder_layerdrop": 0.0,
-      "encoder_layers": 6,
-      "eos_token_id": 2,
-      "forced_eos_token_id": 2,
-      "forced_bos_token_id": 0,
-      "gradient_checkpointing": false,
-      "init_std": 0.02,
-      "is_encoder_decoder": true,
-      "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1,
-        "LABEL_2": 2
-      },
-      "max_position_embeddings": 1024,
-      "no_repeat_ngram_size": 3,
-      "normalize_before": false,
-      "num_hidden_layers": 6,
-      "pad_token_id": 1,
-      "scale_embedding": false,
-      "num_beams": 3
+    "_name_or_path": "",
+    "activation_dropout": 0.1,
+    "activation_function": "gelu",
+    "add_bias_logits": false,
+    "add_cross_attention": false,
+    "add_final_layer_norm": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classif_dropout": 0.1,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 768,
+    "decoder_attention_heads": 12,
+    "decoder_ffn_dim": 3072,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "decoder_start_token_id": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": true,
+    "encoder_attention_heads": 12,
+    "encoder_ffn_dim": 3072,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 6,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": 0,
+    "forced_eos_token_id": 2,
+    "gradient_checkpointing": false,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2"
+    },
+    "init_std": 0.02,
+    "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,
+    "min_length": 0,
+    "model_type": "florence2_language",
+    "no_repeat_ngram_size": 3,
+    "normalize_before": false,
+    "num_beam_groups": 1,
+    "num_beams": 3,
+    "num_hidden_layers": 6,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": 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,
+    "use_cache": true,
+    "vocab_size": 51289
   },
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
   "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
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd4ed2d81363cdb68d8f0d458cc6f37142229d8c52b9ec6494fc97d80f9e4ddd
+oid sha256:606ff85e2917d7cf32e11b5f96ea93bfdb0f025f1c4a297ac82905f441d6c667
 size 1083916964