README.md

@@ -2,8 +2,7 @@
 language: en
 tags:
 - tapex
-- table-question-answering
-license: mit
+license: apache-2.0
 ---
 
 # TAPEX (base-sized model) 
@@ -14,7 +13,7 @@ TAPEX was proposed in [TAPEX: Table Pre-training via Learning a Neural SQL Execu
 
 TAPEX (**Ta**ble **P**re-training via **Ex**ecution) is a conceptually simple and empirically powerful pre-training approach to empower existing models with *table reasoning* skills. TAPEX realizes table pre-training by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesizing executable SQL queries.
 
-TAPEX is based on the BART architecture, the transformer encoder-decoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder.
+TAPEX is based on the BART architecture, the transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder.
 
 ## Intended Uses
 

config.json

@@ -1,9 +1,11 @@
 {
-  "_name_or_path": "microsoft/tapex-base",
+  "_name_or_path": "bart-base",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
   "architectures": [
-    "BartForConditionalGeneration"
+    "BartModel"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 0,
@@ -15,25 +17,57 @@
   "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_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_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
   "max_position_embeddings": 1024,
   "model_type": "bart",
+  "no_repeat_ngram_size": 3,
   "normalize_before": false,
   "normalize_embedding": true,
   "num_beams": 4,
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
   "torch_dtype": "float32",
-  "transformers_version": "4.17.0.dev0",
+  "transformers_version": "4.12.0.dev0",
   "use_cache": true,
   "vocab_size": 50265
 }

generation_config.json

@@ -1,11 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "eos_token_id": 2,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
-  "num_beams": 4,
-  "pad_token_id": 1,
-  "transformers_version": "4.27.0.dev0"
-}

tokenizer_config.json

@@ -1 +0,0 @@
-{"do_lower_case": true, "errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "max_cell_length": 15, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/tapex-base", "tokenizer_class": "TapexTokenizer"}