Upload folder using huggingface_hub

best_info.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2acc66b2f74fa73b4c7d77e883e2409a7740997d450adf5a8a2c8f2e0680d65a
+size 1273

config.json

@@ -0,0 +1,115 @@
+{
+  "architectures": [
+    "InstructBlipForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_index": 32100,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "model_type": "instructblip",
+  "num_query_tokens": 32,
+  "qformer_config": {
+    "attention_probs_dropout_prob": 0.1,
+    "classifier_dropout": null,
+    "cross_attention_frequency": 2,
+    "dtype": "bfloat16",
+    "encoder_hidden_size": 1408,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "instructblip_qformer",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "pad_token_id": 0,
+    "vocab_size": 30523
+  },
+  "text_config": {
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bos_token_id": 1,
+    "classifier_dropout": 0.0,
+    "d_ff": 5120,
+    "d_kv": 64,
+    "d_model": 2048,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu",
+    "dropout_rate": 0.1,
+    "dtype": "bfloat16",
+    "eos_token_id": 1,
+    "feed_forward_proj": "gated-gelu",
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_gated_act": true,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "n_positions": 512,
+    "num_decoder_layers": 24,
+    "num_heads": 32,
+    "num_layers": 24,
+    "output_past": true,
+    "pad_token_id": 0,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "scale_decoder_outputs": false,
+    "task_specific_params": {
+      "summarization": {
+        "early_stopping": true,
+        "length_penalty": 2.0,
+        "max_length": 200,
+        "min_length": 30,
+        "no_repeat_ngram_size": 3,
+        "num_beams": 4,
+        "prefix": "summarize: "
+      },
+      "translation_en_to_de": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to German: "
+      },
+      "translation_en_to_fr": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to French: "
+      },
+      "translation_en_to_ro": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to Romanian: "
+      }
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.1",
+  "use_decoder_only_language_model": false,
+  "video_token_index": 32101,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu",
+    "hidden_size": 1408,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 1e-10,
+    "intermediate_size": 6144,
+    "layer_norm_eps": 1e-06,
+    "model_type": "instructblip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 39,
+    "patch_size": 14,
+    "qkv_bias": true
+  }
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "5.10.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d15773e7d52fc8d32f8e8af1aeaed22f0806491c226d188a2e442605b8c54ac
+size 8046116536

processor_config.json

@@ -0,0 +1,27 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "BlipImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 224,
+      "width": 224
+    }
+  },
+  "num_query_tokens": 32,
+  "processor_class": "InstructBlipProcessor"
+}

qformer_tokenizer/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "[DEC]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "processor_class": "InstructBlipProcessor",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "left",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,117 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "processor_class": "InstructBlipProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>"
+}