Upload folder using huggingface_hub

config.json

@@ -1,26 +1,21 @@
 {
-  "_name_or_path": "./checkpoint-80",
-  "activation_dropout": 0.1,
+  "_name_or_path": "./checkpoint-200",
+  "activation_dropout": 0.0,
   "activation_function": "gelu",
-  "adaptive": true,
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
   "architectures": [
-    "LSGBartForConditionalGeneration"
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
   ],
-  "attention_dropout": 0.1,
-  "auto_map": {
-    "AutoConfig": "modeling_lsg_bart.LSGBartConfig",
-    "AutoModel": "modeling_lsg_bart.LSGBartModel",
-    "AutoModelForCausalLM": "modeling_lsg_bart.LSGBartForCausalLM",
-    "AutoModelForQuestionAnswering": "modeling_lsg_bart.LSGBartForQuestionAnswering",
-    "AutoModelForSeq2SeqLM": "modeling_lsg_bart.LSGBartForConditionalGeneration",
-    "AutoModelForSequenceClassification": "modeling_lsg_bart.LSGBartForSequenceClassification"
-  },
-  "base_model_prefix": "lsg",
-  "block_size": 128,
   "bos_token_id": 0,
-  "classif_dropout": 0.1,
+  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
   "d_model": 768,
   "decoder_attention_heads": 12,
@@ -35,8 +30,6 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -49,47 +42,17 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "lsh_num_pre_rounds": 1,
-  "mask_first_token": false,
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
   "max_length": 384,
-  "max_position_embeddings": 4096,
   "min_length": 100,
-  "model_type": "bart",
+  "model_type": "led",
   "no_repeat_ngram_size": 3,
-  "normalize_before": false,
-  "normalize_embedding": true,
   "num_beams": 2,
-  "num_global_tokens": 1,
   "num_hidden_layers": 6,
   "pad_token_id": 1,
-  "pass_global_tokens_to_decoder": true,
-  "pool_with_global": true,
-  "scale_embedding": false,
-  "sparse_block_size": 128,
-  "sparsity_factor": 2,
-  "sparsity_type": "norm",
-  "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": "4.30.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 50265
 }

generation_config.json

@@ -3,8 +3,6 @@
   "decoder_start_token_id": 2,
   "early_stopping": true,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
   "max_length": 384,
   "min_length": 100,
   "no_repeat_ngram_size": 3,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b47951d6fe49cb468c855de22d75afb7c96d3c3befb69abf3398eb3de1e51750
-size 578415073
+oid sha256:31c85199ff57a7b76bd8d8ae90ac7a51fbd9eeb88e519b2aeca892be70a66c76
+size 647676653

special_tokens_map.json

@@ -1,15 +1,51 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -23,7 +23,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -32,7 +32,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -41,7 +41,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -50,7 +50,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -59,7 +59,7 @@
       "single_word": false,
       "lstrip": true,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     }
   ],

tokenizer_config.json

@@ -1,15 +1,64 @@
 {
   "add_prefix_space": false,
-  "bos_token": "<s>",
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 4096,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "BartTokenizer",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 16384,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "LEDTokenizer",
   "trim_offsets": true,
-  "unk_token": "<unk>"
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }