Upload Pix2StructForConditionalGeneration

config.json

@@ -1,5 +1,4 @@
 {
-  "_commit_hash": "8a3e42420c3465a9e98441bdf84fe70b59d57cb8",
   "_name_or_path": "google/matcha-base",
   "architectures": [
     "Pix2StructForConditionalGeneration"
@@ -13,168 +12,19 @@
   "model_type": "pix2struct",
   "pad_token_id": 0,
   "text_config": {
-    "_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,
-    "d_ff": 2048,
-    "d_kv": 64,
-    "decoder_start_token_id": 0,
-    "dense_act_fn": "gelu_new",
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout_rate": 0.1,
-    "early_stopping": false,
     "encoder_hidden_size": 768,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 1,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "is_decoder": true,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_epsilon": 1e-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "pix2struct_text_model",
-    "no_repeat_ngram_size": 0,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_heads": 12,
-    "num_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 0,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "relative_attention_max_distance": 128,
-    "relative_attention_num_buckets": 32,
-    "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": false,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "transformers_version": "4.29.2",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": false,
-    "vocab_size": 50244
+    "model_type": "pix2struct_text_model"
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": null,
+  "transformers_version": "4.32.1",
   "vision_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "d_ff": 2048,
-    "d_kv": 64,
-    "decoder_start_token_id": null,
-    "dense_act_fn": "gelu_new",
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout_rate": 0.0,
-    "early_stopping": 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,
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
     "layer_norm_bias": false,
-    "layer_norm_eps": 1e-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
     "model_type": "pix2struct_vision_model",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_channels": 3,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_embed_hidden_size": 768,
     "patch_size": 16,
-    "prefix": null,
-    "problem_type": null,
-    "projection_dim": 768,
-    "pruned_heads": {},
-    "relative_attention_max_distance": 128,
-    "relative_attention_num_buckets": 32,
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "seq_len": 4096,
-    "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,
-    "transformers_version": "4.29.2",
-    "typical_p": 1.0,
-    "use_bfloat16": false
+    "projection_dim": 768
   }
 }

generation_config.json

@@ -3,6 +3,6 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.32.1",
   "use_cache": false
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46adceccab18a8ce210134f1953a1d8e57b2dbc8a81e11463d52950c3085fbd8
+oid sha256:772810c183dde787b9e141eba3a3eba77a559990941c0a0a0785e8edaff71f15
 size 1129242049