Update tiny models for Pix2StructForConditionalGeneration

Browse files

Files changed (6) hide show

config.json +71 -0
generation_config.json +11 -0
model.safetensors +3 -0
preprocessor_config.json +19 -0
tokenizer.json +0 -0
tokenizer_config.json +115 -0

config.json ADDED Viewed

	@@ -0,0 +1,71 @@

+{
+  "architectures": [
+    "Pix2StructForConditionalGeneration"
+  ],
+  "decoder_start_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "is_vqa": false,
+  "model_type": "pix2struct",
+  "pad_token_id": 0,
+  "projection_dim": 64,
+  "text_config": {
+    "add_cross_attention": false,
+    "attention_dropout": 0.1,
+    "bos_token_id": 0,
+    "d_ff": 2048,
+    "d_kv": 3,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "dropout": 0.1,
+    "dropout_rate": 0.1,
+    "eos_token_id": 1,
+    "hidden_size": 12,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": true,
+    "is_encoder_decoder": true,
+    "layer_norm_epsilon": 1e-06,
+    "max_position_embeddings": 512,
+    "model_type": "pix2struct_text_model",
+    "num_heads": 4,
+    "num_layers": 2,
+    "pad_token_id": 0,
+    "projection_dim": 32,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "tie_word_embeddings": false,
+    "use_cache": false,
+    "vocab_size": 50344
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.1,
+    "d_ff": 2048,
+    "d_kv": 64,
+    "dense_act_fn": "gelu_new",
+    "dropout": 0.1,
+    "dropout_rate": 0.0,
+    "hidden_size": 12,
+    "image_size": 30,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_norm_eps": 1e-06,
+    "model_type": "pix2struct_vision_model",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_embed_hidden_size": 12,
+    "patch_size": 2,
+    "projection_dim": 32,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "seq_len": 4096
+  }
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": false
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b1f882656956e3a7a46e2e309023fc77a542c9179010397467f781236bcc99
+size 6521528

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,19 @@

+{
+  "crop_size": {
+    "height": 30,
+    "width": 30
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "image_processor_type": "Pix2StructImageProcessor",
+  "is_vqa": false,
+  "max_patches": 2048,
+  "patch_size": {
+    "height": 16,
+    "width": 16
+  },
+  "size": {
+    "height": 30,
+    "width": 30
+  }
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,115 @@

+{
+  "backend": "tokenizers",
+  "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": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Pix2StructProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}