Update tiny models for PPFormulaNetForConditionalGeneration

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "PPFormulaNetForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "is_encoder_decoder": true,
+  "model_type": "pp_formulanet",
+  "num_hidden_layers": 1,
+  "text_config": {
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "d_model": 48,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 16,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 1,
+    "decoder_start_token_id": 2,
+    "dropout": 0.1,
+    "encoder_attention_heads": 16,
+    "encoder_layers": 12,
+    "eos_token_id": 2,
+    "forced_eos_token_id": 2,
+    "init_std": 0.02,
+    "max_position_embeddings": 2560,
+    "model_type": "pp_formulanet",
+    "pad_token_id": 1,
+    "scale_embedding": true,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 50000
+  },
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "decoder_hidden_size": 48,
+    "global_attn_indexes": [
+      1,
+      1,
+      1,
+      1
+    ],
+    "hidden_act": "gelu",
+    "hidden_size": 48,
+    "image_size": 768,
+    "initializer_range": 1e-10,
+    "layer_norm_eps": 1e-06,
+    "mlp_dim": 1,
+    "model_type": "",
+    "num_attention_heads": 2,
+    "num_channels": 3,
+    "num_hidden_layers": 1,
+    "output_channels": 16,
+    "patch_size": 16,
+    "post_conv_in_channels": 16,
+    "post_conv_mid_channels": 16,
+    "post_conv_out_channels": 16,
+    "qkv_bias": true,
+    "use_abs_pos": true,
+    "use_rel_pos": true,
+    "window_size": 14,
+    "windows_size": 14
+  }
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 1,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5524a1262cc2264593d3f86ac1172b7503c7f60d22d88ffe19709e30db84a19
+size 20451836

preprocessor_config.json

@@ -0,0 +1,30 @@
+{
+  "crop_size": {
+    "height": 768,
+    "width": 768
+  },
+  "do_align_long_axis": false,
+  "do_crop_margin": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "image_mean": [
+    0.7931,
+    0.7931,
+    0.7931
+  ],
+  "image_processor_type": "PPFormulaNetImageProcessor",
+  "image_std": [
+    0.1738,
+    0.1738,
+    0.1738
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 768,
+    "width": 768
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": true,
+  "local_files_only": false,
+  "max_length": 4096,
+  "model_max_length": 768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "NougatProcessor",
+  "stride": 0,
+  "tokenizer_class": "NougatTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}