Upload BartForConditionalGeneration

config.json

@@ -1,75 +1,56 @@
 {
-  "_name_or_path": "./canvers-en2ko-v1.0",
-  "activation_dropout": 0.1,
+  "_name_or_path": "./output3/checkpoint-12100000",
+  "activation_dropout": 0.0,
   "activation_function": "gelu",
   "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
+  "attention_dropout": 0.0,
+  "author": "Heewon Jeon([email protected])",
+  "bos_token_id": 1,
   "classif_dropout": 0.1,
-  "classifier_dropout": 0.0,
+  "classifier_dropout": 0.1,
   "d_model": 768,
-  "decoder_attention_heads": 12,
+  "decoder_attention_heads": 16,
   "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
-  "decoder_start_token_id": 2,
+  "decoder_start_token_id": 1,
+  "do_blenderbot_90_layernorm": false,
   "dropout": 0.1,
-  "early_stopping": true,
-  "encoder_attention_heads": 12,
+  "encoder_attention_heads": 16,
   "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,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 1,
   "gradient_checkpointing": false,
   "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
   },
   "init_std": 0.02,
   "is_encoder_decoder": true,
+  "kobart_version": 2.0,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
+    "NEGATIVE": 0,
+    "POSITIVE": 1
   },
-  "max_position_embeddings": 1024,
+  "max_position_embeddings": 1026,
   "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,
+  "pad_token_id": 3,
   "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
-    }
-  },
+  "static_position_embeddings": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "torch_dtype": "float32",
   "transformers_version": "4.29.1",
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30000
 }

generation_config.json

@@ -1,13 +1,9 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "early_stopping": true,
-  "eos_token_id": 2,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 4,
-  "pad_token_id": 1,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "pad_token_id": 3,
   "transformers_version": "4.29.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:837065718ace2c331ea824e47e555ff3b2e3258d6045cb96b281f4f8a25d4bac
-size 557967517
+oid sha256:4d17c0a510c3fad83177a740effa2160b81ab91a425a05c88c7b5434a23e3624
+size 495644701