Test V1

config.json

@@ -1,66 +1,31 @@
 {
-  "_name_or_path": "facebook/bart-large-xsum",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
+  "_name_or_path": "google/mt5-base",
   "architectures": [
-    "BartForConditionalGeneration"
+    "MT5ForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "early_stopping": true,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
-  "eos_token_id": 2,
-  "eos_token_ids": [
-    2
-  ],
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_length": 62,
-  "max_position_embeddings": 1024,
-  "min_length": 11,
-  "model_type": "bart",
-  "no_repeat_ngram_size": 3,
-  "normalize_before": false,
-  "normalize_embedding": true,
-  "num_beams": 6,
-  "num_hidden_layers": 12,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 84,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 4,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
-  "pad_token_id": 1,
-  "prefix": " ",
-  "replacing_rate": 0,
-  "scale_embedding": false,
-  "static_position_embeddings": false,
-  "student_decoder_layers": null,
-  "student_encoder_layers": null,
-  "task_specific_params": {},
-  "transformers_version": "4.6.1",
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
   "use_cache": true,
-  "vocab_size": 50264
+  "vocab_size": 250112
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c321394e634dfcc74b8344b3b898931977cfda1ace1d11f0c78027dbfd86ddb
-size 1625565295
+oid sha256:1899a041aceedfd0c9c67e87f2597bc597ce6f4c1f21b5d35a6325322608a898
+size 2329707353

special_tokens_map.json

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

model.safetensors → spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29acd5ae506056667cd4bf53a9dbbf36f9016937248f6e4b7dd6f319b2f460f1
-size 1625422896
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large-xsum"}
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "tokenizer_file": null, "name_or_path": "google/mt5-base"}