Upload 45 files

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+gervasio/model/model/training_progress.json filter=lfs diff=lfs merge=lfs -text
+gervasio/nohup.out filter=lfs diff=lfs merge=lfs -text
+sabia/model/model/training_progress.json filter=lfs diff=lfs merge=lfs -text
+sabia/nohup.out filter=lfs diff=lfs merge=lfs -text

bart/model/config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "adalbertojunior/bart-base-portuguese",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "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": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

bart/model/events.out.tfevents.1725577804.savio.7542.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb00df6b0cf72d7d1105bae43bc676b9cbf39af976e6246ed73ce93730924f8
+size 54970

bart/model/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_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,
+  "transformers_version": "4.44.2"
+}

bart/model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2a940ff0adda6d7c46324a667106ea47b76095f59ea178e85f366ec4795ca15
+size 557912620

bart/model/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

bart/model/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

byt5/model/added_tokens.json

@@ -0,0 +1,127 @@
+{
+  "<extra_id_0>": 259,
+  "<extra_id_100>": 359,
+  "<extra_id_101>": 360,
+  "<extra_id_102>": 361,
+  "<extra_id_103>": 362,
+  "<extra_id_104>": 363,
+  "<extra_id_105>": 364,
+  "<extra_id_106>": 365,
+  "<extra_id_107>": 366,
+  "<extra_id_108>": 367,
+  "<extra_id_109>": 368,
+  "<extra_id_10>": 269,
+  "<extra_id_110>": 369,
+  "<extra_id_111>": 370,
+  "<extra_id_112>": 371,
+  "<extra_id_113>": 372,
+  "<extra_id_114>": 373,
+  "<extra_id_115>": 374,
+  "<extra_id_116>": 375,
+  "<extra_id_117>": 376,
+  "<extra_id_118>": 377,
+  "<extra_id_119>": 378,
+  "<extra_id_11>": 270,
+  "<extra_id_120>": 379,
+  "<extra_id_121>": 380,
+  "<extra_id_122>": 381,
+  "<extra_id_123>": 382,
+  "<extra_id_124>": 383,
+  "<extra_id_12>": 271,
+  "<extra_id_13>": 272,
+  "<extra_id_14>": 273,
+  "<extra_id_15>": 274,
+  "<extra_id_16>": 275,
+  "<extra_id_17>": 276,
+  "<extra_id_18>": 277,
+  "<extra_id_19>": 278,
+  "<extra_id_1>": 260,
+  "<extra_id_20>": 279,
+  "<extra_id_21>": 280,
+  "<extra_id_22>": 281,
+  "<extra_id_23>": 282,
+  "<extra_id_24>": 283,
+  "<extra_id_25>": 284,
+  "<extra_id_26>": 285,
+  "<extra_id_27>": 286,
+  "<extra_id_28>": 287,
+  "<extra_id_29>": 288,
+  "<extra_id_2>": 261,
+  "<extra_id_30>": 289,
+  "<extra_id_31>": 290,
+  "<extra_id_32>": 291,
+  "<extra_id_33>": 292,
+  "<extra_id_34>": 293,
+  "<extra_id_35>": 294,
+  "<extra_id_36>": 295,
+  "<extra_id_37>": 296,
+  "<extra_id_38>": 297,
+  "<extra_id_39>": 298,
+  "<extra_id_3>": 262,
+  "<extra_id_40>": 299,
+  "<extra_id_41>": 300,
+  "<extra_id_42>": 301,
+  "<extra_id_43>": 302,
+  "<extra_id_44>": 303,
+  "<extra_id_45>": 304,
+  "<extra_id_46>": 305,
+  "<extra_id_47>": 306,
+  "<extra_id_48>": 307,
+  "<extra_id_49>": 308,
+  "<extra_id_4>": 263,
+  "<extra_id_50>": 309,
+  "<extra_id_51>": 310,
+  "<extra_id_52>": 311,
+  "<extra_id_53>": 312,
+  "<extra_id_54>": 313,
+  "<extra_id_55>": 314,
+  "<extra_id_56>": 315,
+  "<extra_id_57>": 316,
+  "<extra_id_58>": 317,
+  "<extra_id_59>": 318,
+  "<extra_id_5>": 264,
+  "<extra_id_60>": 319,
+  "<extra_id_61>": 320,
+  "<extra_id_62>": 321,
+  "<extra_id_63>": 322,
+  "<extra_id_64>": 323,
+  "<extra_id_65>": 324,
+  "<extra_id_66>": 325,
+  "<extra_id_67>": 326,
+  "<extra_id_68>": 327,
+  "<extra_id_69>": 328,
+  "<extra_id_6>": 265,
+  "<extra_id_70>": 329,
+  "<extra_id_71>": 330,
+  "<extra_id_72>": 331,
+  "<extra_id_73>": 332,
+  "<extra_id_74>": 333,
+  "<extra_id_75>": 334,
+  "<extra_id_76>": 335,
+  "<extra_id_77>": 336,
+  "<extra_id_78>": 337,
+  "<extra_id_79>": 338,
+  "<extra_id_7>": 266,
+  "<extra_id_80>": 339,
+  "<extra_id_81>": 340,
+  "<extra_id_82>": 341,
+  "<extra_id_83>": 342,
+  "<extra_id_84>": 343,
+  "<extra_id_85>": 344,
+  "<extra_id_86>": 345,
+  "<extra_id_87>": 346,
+  "<extra_id_88>": 347,
+  "<extra_id_89>": 348,
+  "<extra_id_8>": 267,
+  "<extra_id_90>": 349,
+  "<extra_id_91>": 350,
+  "<extra_id_92>": 351,
+  "<extra_id_93>": 352,
+  "<extra_id_94>": 353,
+  "<extra_id_95>": 354,
+  "<extra_id_96>": 355,
+  "<extra_id_97>": 356,
+  "<extra_id_98>": 357,
+  "<extra_id_99>": 358,
+  "<extra_id_9>": 268
+}

byt5/model/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "pierreguillou/byt5-small-qa-squad-v1.1-portuguese",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3584,
+  "d_kv": 64,
+  "d_model": 1472,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 4,
+  "num_heads": 6,
+  "num_layers": 12,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "text2text-generation": {
+      "max_length": 64,
+      "num_beams": 1,
+      "prefix": ""
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "ByT5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 384
+}

byt5/model/events.out.tfevents.1725905553.savio.255141.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813fb737a0ff077870f9e31f84ad261612759a52433e45cdabd000e85595dbeb
+size 403482

byt5/model/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2",
+  "use_cache": false
+}

byt5/model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c613b8d7e9d9ba7efe12c8460952e6ad360b2895a9fee0db17ee838cbe151e
+size 1198571496

byt5/model/special_tokens_map.json

@@ -0,0 +1,150 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>",
+    "<extra_id_100>",
+    "<extra_id_101>",
+    "<extra_id_102>",
+    "<extra_id_103>",
+    "<extra_id_104>",
+    "<extra_id_105>",
+    "<extra_id_106>",
+    "<extra_id_107>",
+    "<extra_id_108>",
+    "<extra_id_109>",
+    "<extra_id_110>",
+    "<extra_id_111>",
+    "<extra_id_112>",
+    "<extra_id_113>",
+    "<extra_id_114>",
+    "<extra_id_115>",
+    "<extra_id_116>",
+    "<extra_id_117>",
+    "<extra_id_118>",
+    "<extra_id_119>",
+    "<extra_id_120>",
+    "<extra_id_121>",
+    "<extra_id_122>",
+    "<extra_id_123>",
+    "<extra_id_124>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

byt5/model/tokenizer_config.json

@@ -0,0 +1,1162 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "259": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "260": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "262": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "263": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "264": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "265": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "266": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "267": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "268": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "269": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "270": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "271": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "272": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "273": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "274": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "275": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "276": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "277": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "278": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "279": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "280": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "281": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "282": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "283": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "284": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "285": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "286": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "287": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "288": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "289": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "290": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "291": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "292": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "293": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "294": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "295": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "296": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "297": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "298": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "299": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "300": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "301": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "302": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "303": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "304": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "305": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "306": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "307": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "308": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "309": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "310": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "311": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "312": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "313": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "314": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "315": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "316": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "317": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "318": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "319": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "320": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "321": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "322": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "323": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "324": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "325": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "326": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "327": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "328": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "329": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "330": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "331": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "332": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "333": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "334": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "335": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "336": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "337": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "338": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "339": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "340": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "341": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "342": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "343": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "344": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "345": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "346": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "347": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "348": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "349": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "350": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "351": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "352": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "353": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "354": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "355": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "356": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "357": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "358": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "359": {
+      "content": "<extra_id_100>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "360": {
+      "content": "<extra_id_101>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "361": {
+      "content": "<extra_id_102>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "362": {
+      "content": "<extra_id_103>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "363": {
+      "content": "<extra_id_104>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "364": {
+      "content": "<extra_id_105>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "365": {
+      "content": "<extra_id_106>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "366": {
+      "content": "<extra_id_107>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "367": {
+      "content": "<extra_id_108>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "368": {
+      "content": "<extra_id_109>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "369": {
+      "content": "<extra_id_110>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "370": {
+      "content": "<extra_id_111>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "371": {
+      "content": "<extra_id_112>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "372": {
+      "content": "<extra_id_113>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "373": {
+      "content": "<extra_id_114>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "374": {
+      "content": "<extra_id_115>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "375": {
+      "content": "<extra_id_116>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "376": {
+      "content": "<extra_id_117>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "377": {
+      "content": "<extra_id_118>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "378": {
+      "content": "<extra_id_119>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "379": {
+      "content": "<extra_id_120>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "380": {
+      "content": "<extra_id_121>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "381": {
+      "content": "<extra_id_122>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "382": {
+      "content": "<extra_id_123>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "383": {
+      "content": "<extra_id_124>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>",
+    "<extra_id_100>",
+    "<extra_id_101>",
+    "<extra_id_102>",
+    "<extra_id_103>",
+    "<extra_id_104>",
+    "<extra_id_105>",
+    "<extra_id_106>",
+    "<extra_id_107>",
+    "<extra_id_108>",
+    "<extra_id_109>",
+    "<extra_id_110>",
+    "<extra_id_111>",
+    "<extra_id_112>",
+    "<extra_id_113>",
+    "<extra_id_114>",
+    "<extra_id_115>",
+    "<extra_id_116>",
+    "<extra_id_117>",
+    "<extra_id_118>",
+    "<extra_id_119>",
+    "<extra_id_120>",
+    "<extra_id_121>",
+    "<extra_id_122>",
+    "<extra_id_123>",
+    "<extra_id_124>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "ByT5Tokenizer",
+  "unk_token": "<unk>"
+}

gervasio/model/description.json

@@ -0,0 +1,358 @@
+{
+    "command": "fine_tuning.py",
+    "compute": {
+        "arch_list": [
+            "sm_50",
+            "sm_60",
+            "sm_70",
+            "sm_75",
+            "sm_80",
+            "sm_86",
+            "sm_90"
+        ],
+        "devices": {
+            "0": {
+                "device_capability": [
+                    6,
+                    1
+                ],
+                "device_properties": "_CudaDeviceProperties(name='NVIDIA TITAN Xp', major=6, minor=1, total_memory=12188MB, multi_processor_count=30)",
+                "gpu_type": "NVIDIA TITAN Xp"
+            }
+        },
+        "gencode_flags": "-gencode compute=compute_50,code=sm_50 -gencode compute=compute_60,code=sm_60 -gencode compute=compute_70,code=sm_70 -gencode compute=compute_75,code=sm_75 -gencode compute=compute_80,code=sm_80 -gencode compute=compute_86,code=sm_86 -gencode compute=compute_90,code=sm_90",
+        "gpus_per_node": 1,
+        "num_nodes": 1
+    },
+    "config": {
+        "adapter": {
+            "alpha": 16,
+            "bias_type": "none",
+            "dropout": 0.05,
+            "postprocessor": {
+                "merge_adapter_into_base_model": false,
+                "progressbar": false
+            },
+            "pretrained_adapter_weights": null,
+            "r": 8,
+            "target_modules": null,
+            "type": "lora",
+            "use_dora": false,
+            "use_rslora": false
+        },
+        "backend": null,
+        "base_model": "PORTULAN/gervasio-7b-portuguese-ptbr-decoder",
+        "defaults": {
+            "text": {
+                "decoder": {
+                    "fc_activation": "relu",
+                    "fc_bias_initializer": "zeros",
+                    "fc_dropout": 0.0,
+                    "fc_layers": null,
+                    "fc_norm": null,
+                    "fc_norm_params": null,
+                    "fc_output_size": 256,
+                    "fc_use_bias": true,
+                    "fc_weights_initializer": "xavier_uniform",
+                    "input_size": null,
+                    "max_new_tokens": null,
+                    "num_fc_layers": 0,
+                    "pretrained_model_name_or_path": "",
+                    "tokenizer": "hf_tokenizer",
+                    "type": "text_extractor",
+                    "vocab_file": ""
+                },
+                "encoder": {
+                    "skip": false,
+                    "type": "passthrough"
+                },
+                "loss": {
+                    "class_similarities": null,
+                    "class_similarities_temperature": 0,
+                    "class_weights": null,
+                    "confidence_penalty": 0,
+                    "robust_lambda": 0,
+                    "type": "next_token_softmax_cross_entropy",
+                    "unique": false,
+                    "weight": 1.0
+                },
+                "preprocessing": {
+                    "cache_encoder_embeddings": false,
+                    "compute_idf": false,
+                    "computed_fill_value": "<UNK>",
+                    "fill_value": "<UNK>",
+                    "lowercase": false,
+                    "max_sequence_length": 256,
+                    "missing_value_strategy": "fill_with_const",
+                    "most_common": 20000,
+                    "ngram_size": 2,
+                    "padding": "right",
+                    "padding_symbol": "<PAD>",
+                    "pretrained_model_name_or_path": null,
+                    "prompt": {
+                        "retrieval": {
+                            "index_name": null,
+                            "k": 0,
+                            "model_name": null,
+                            "type": null
+                        },
+                        "task": null,
+                        "template": null
+                    },
+                    "sequence_length": null,
+                    "tokenizer": "space_punct",
+                    "unknown_symbol": "<UNK>",
+                    "vocab_file": null
+                }
+            }
+        },
+        "generation": {
+            "bad_words_ids": null,
+            "begin_suppress_tokens": null,
+            "bos_token_id": null,
+            "diversity_penalty": 0.0,
+            "do_sample": true,
+            "early_stopping": false,
+            "encoder_repetition_penalty": 1.0,
+            "eos_token_id": null,
+            "epsilon_cutoff": 0.0,
+            "eta_cutoff": 0.0,
+            "exponential_decay_length_penalty": null,
+            "force_words_ids": null,
+            "forced_bos_token_id": null,
+            "forced_decoder_ids": null,
+            "forced_eos_token_id": null,
+            "guidance_scale": null,
+            "length_penalty": 1.0,
+            "max_length": 32,
+            "max_new_tokens": 200,
+            "max_time": null,
+            "min_length": 0,
+            "min_new_tokens": null,
+            "no_repeat_ngram_size": 0,
+            "num_beam_groups": 1,
+            "num_beams": 1,
+            "pad_token_id": null,
+            "penalty_alpha": null,
+            "prompt_lookup_num_tokens": null,
+            "remove_invalid_values": false,
+            "renormalize_logits": false,
+            "repetition_penalty": 1.0,
+            "sequence_bias": null,
+            "suppress_tokens": null,
+            "temperature": 0.001,
+            "top_k": 50,
+            "top_p": 1.0,
+            "typical_p": 1.0,
+            "use_cache": true
+        },
+        "hyperopt": null,
+        "input_features": [
+            {
+                "active": true,
+                "column": "input",
+                "encoder": {
+                    "skip": false,
+                    "type": "passthrough"
+                },
+                "name": "input",
+                "preprocessing": {
+                    "cache_encoder_embeddings": false,
+                    "compute_idf": false,
+                    "computed_fill_value": "<UNK>",
+                    "fill_value": "<UNK>",
+                    "lowercase": false,
+                    "max_sequence_length": null,
+                    "missing_value_strategy": "fill_with_const",
+                    "most_common": 20000,
+                    "ngram_size": 2,
+                    "padding": "left",
+                    "padding_symbol": "<PAD>",
+                    "pretrained_model_name_or_path": "PORTULAN/gervasio-7b-portuguese-ptbr-decoder",
+                    "sequence_length": null,
+                    "tokenizer": "hf_tokenizer",
+                    "unknown_symbol": "<UNK>",
+                    "vocab_file": null
+                },
+                "proc_column": "input_dWJgst",
+                "tied": null,
+                "type": "text"
+            }
+        ],
+        "ludwig_version": "0.10.4",
+        "model_parameters": null,
+        "model_type": "llm",
+        "output_features": [
+            {
+                "active": true,
+                "class_similarities": null,
+                "column": "output",
+                "decoder": {
+                    "fc_activation": "relu",
+                    "fc_bias_initializer": "zeros",
+                    "fc_dropout": 0.0,
+                    "fc_layers": null,
+                    "fc_norm": null,
+                    "fc_norm_params": null,
+                    "fc_output_size": 256,
+                    "fc_use_bias": true,
+                    "fc_weights_initializer": "xavier_uniform",
+                    "input_size": null,
+                    "max_new_tokens": 200,
+                    "num_fc_layers": 0,
+                    "pretrained_model_name_or_path": "PORTULAN/gervasio-7b-portuguese-ptbr-decoder",
+                    "tokenizer": "hf_tokenizer",
+                    "type": "text_extractor",
+                    "vocab_file": ""
+                },
+                "default_validation_metric": "loss",
+                "dependencies": [],
+                "input_size": null,
+                "loss": {
+                    "class_similarities": null,
+                    "class_similarities_temperature": 0,
+                    "class_weights": null,
+                    "confidence_penalty": 0,
+                    "robust_lambda": 0,
+                    "type": "next_token_softmax_cross_entropy",
+                    "unique": false,
+                    "weight": 1.0
+                },
+                "name": "output",
+                "num_classes": null,
+                "preprocessing": {
+                    "cache_encoder_embeddings": false,
+                    "compute_idf": false,
+                    "computed_fill_value": "<UNK>",
+                    "fill_value": "<UNK>",
+                    "lowercase": false,
+                    "max_sequence_length": null,
+                    "missing_value_strategy": "drop_row",
+                    "most_common": 20000,
+                    "ngram_size": 2,
+                    "padding": "left",
+                    "padding_symbol": "<PAD>",
+                    "pretrained_model_name_or_path": "PORTULAN/gervasio-7b-portuguese-ptbr-decoder",
+                    "sequence_length": null,
+                    "tokenizer": "hf_tokenizer",
+                    "unknown_symbol": "<UNK>",
+                    "vocab_file": null
+                },
+                "proc_column": "output_QRMBIj",
+                "reduce_dependencies": "sum",
+                "reduce_input": "sum",
+                "type": "text"
+            }
+        ],
+        "preprocessing": {
+            "global_max_sequence_length": null,
+            "oversample_minority": null,
+            "sample_ratio": 1.0,
+            "sample_size": null,
+            "split": {
+                "probabilities": [
+                    0.9,
+                    0.1,
+                    0.0
+                ],
+                "type": "random"
+            },
+            "undersample_majority": null
+        },
+        "prompt": {
+            "retrieval": {
+                "index_name": null,
+                "k": 0,
+                "model_name": null,
+                "type": null
+            },
+            "task": null,
+            "template": "### Instru\u00e7\u00e3o: Voc\u00ea receber\u00e1 o texto de uma reda\u00e7\u00e3o extra\u00edda por um sistema de OCR. Corrija os erros presentes no texto.\n### Entrada: {input}\n### Resposta:"
+        },
+        "quantization": {
+            "bits": 4,
+            "bnb_4bit_compute_dtype": "float16",
+            "bnb_4bit_quant_type": "nf4",
+            "bnb_4bit_use_double_quant": true,
+            "llm_int8_has_fp16_weight": false,
+            "llm_int8_threshold": 6.0
+        },
+        "trainer": {
+            "base_learning_rate": 0.0,
+            "batch_size": 1,
+            "bucketing_field": null,
+            "checkpoints_per_epoch": 0,
+            "compile": false,
+            "early_stop": 5,
+            "effective_batch_size": "auto",
+            "enable_gradient_checkpointing": false,
+            "enable_profiling": false,
+            "epochs": 1,
+            "eval_batch_size": 1,
+            "eval_steps": null,
+            "evaluate_training_set": false,
+            "gradient_accumulation_steps": 16,
+            "gradient_clipping": {
+                "clipglobalnorm": 0.5,
+                "clipnorm": null,
+                "clipvalue": null
+            },
+            "increase_batch_size_eval_metric": "loss",
+            "increase_batch_size_eval_split": "training",
+            "increase_batch_size_on_plateau": 0,
+            "increase_batch_size_on_plateau_patience": 5,
+            "increase_batch_size_on_plateau_rate": 2.0,
+            "layers_to_freeze_regex": null,
+            "learning_rate": 0.0001,
+            "learning_rate_scaling": "linear",
+            "learning_rate_scheduler": {
+                "decay": null,
+                "decay_rate": 0.96,
+                "decay_steps": 10000,
+                "eta_min": 0,
+                "reduce_eval_metric": "loss",
+                "reduce_eval_split": "training",
+                "reduce_on_plateau": 0,
+                "reduce_on_plateau_patience": 10,
+                "reduce_on_plateau_rate": 0.1,
+                "staircase": false,
+                "t_0": null,
+                "t_mult": 1,
+                "warmup_evaluations": 0,
+                "warmup_fraction": 0.03
+            },
+            "max_batch_size": 1099511627776,
+            "optimizer": {
+                "amsgrad": false,
+                "betas": [
+                    0.9,
+                    0.999
+                ],
+                "eps": 1e-08,
+                "type": "adam",
+                "weight_decay": 0.0
+            },
+            "profiler": {
+                "active": 3,
+                "repeat": 5,
+                "skip_first": 0,
+                "wait": 1,
+                "warmup": 1
+            },
+            "regularization_lambda": 0.0,
+            "regularization_type": "l2",
+            "should_shuffle": true,
+            "skip_all_evaluation": false,
+            "steps_per_checkpoint": 0,
+            "train_steps": null,
+            "type": "finetune",
+            "use_mixed_precision": false,
+            "validation_field": "output",
+            "validation_metric": "loss"
+        }
+    },
+    "data_format": "<class 'pandas.core.frame.DataFrame'>",
+    "ludwig_version": "0.10.4",
+    "random_seed": 42,
+    "torch_version": "2.2.2+cu121"
+}

gervasio/model/model/logs/training/events.out.tfevents.1725963146.user-System-Product-Name.62720.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ee720459028ab5fb595fdef8a2281b6b65657d68240d03f3549ac062eeec8e
+size 314339737

gervasio/model/model/logs/validation/events.out.tfevents.1725963146.user-System-Product-Name.62720.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e759bad2a4a063a4f0a15752ee98be63338a898e57dd043272860cb07e4f938e
+size 478

gervasio/model/model/model_weights/README.md

@@ -0,0 +1,202 @@
+---
+base_model: PORTULAN/gervasio-7b-portuguese-ptbr-decoder
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

gervasio/model/model/model_weights/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "PORTULAN/gervasio-7b-portuguese-ptbr-decoder",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

gervasio/model/model/model_weights/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd5482b9a73c88bdc5db24e7a820a584ceccfd1c3e05abc037c17e454d3b5e1
+size 16794200

gervasio/model/model/training_checkpoints/best.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc4821922d86d5e738d1cb0d2bdb162c5c6f0a60c50ee935a2515464be8eaf8
+size 50556326

gervasio/model/model/training_checkpoints/latest.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc4821922d86d5e738d1cb0d2bdb162c5c6f0a60c50ee935a2515464be8eaf8
+size 50556326

gervasio/model/model/training_progress.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67dcb6e48ca6ac38ba6377eb4b0ca0f6d656f4ea60a6f628c6cb4adcb161c77d
+size 10988199

gervasio/model/training_statistics.json

@@ -0,0 +1,55 @@
+{
+    "evaluation_frequency": {
+        "frequency": 1,
+        "period": "epoch"
+    },
+    "test": {},
+    "training": {
+        "combined": {
+            "loss": [
+                0.3331681191921234
+            ]
+        },
+        "output": {
+            "loss": [
+                0.3331681191921234
+            ],
+            "next_token_perplexity": [
+                13091.435546875
+            ],
+            "perplexity": [
+                30826.7109375
+            ],
+            "sequence_accuracy": [
+                0.0
+            ],
+            "token_accuracy": [
+                0.00020183049491606653
+            ]
+        }
+    },
+    "validation": {
+        "combined": {
+            "loss": [
+                0.26174962520599365
+            ]
+        },
+        "output": {
+            "loss": [
+                0.26174962520599365
+            ],
+            "next_token_perplexity": [
+                12883.8994140625
+            ],
+            "perplexity": [
+                30791.365234375
+            ],
+            "sequence_accuracy": [
+                0.0
+            ],
+            "token_accuracy": [
+                0.00018106875359080732
+            ]
+        }
+    }
+}

gervasio/nohup.out

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49eeb88f11a7c63e7b76060a0224f9a9f8a15282bed5af065640fac00596460e
+size 41861772

sabia/model/description.json

@@ -0,0 +1,357 @@
+{
+    "command": "fine_tuning.py",
+    "compute": {
+        "arch_list": [
+            "sm_50",
+            "sm_60",
+            "sm_70",
+            "sm_75",
+            "sm_80",
+            "sm_86",
+            "sm_90"
+        ],
+        "devices": {
+            "0": {
+                "device_capability": [
+                    6,
+                    1
+                ],
+                "device_properties": "_CudaDeviceProperties(name='NVIDIA TITAN Xp', major=6, minor=1, total_memory=12188MB, multi_processor_count=30)",
+                "gpu_type": "NVIDIA TITAN Xp"
+            }
+        },
+        "gencode_flags": "-gencode compute=compute_50,code=sm_50 -gencode compute=compute_60,code=sm_60 -gencode compute=compute_70,code=sm_70 -gencode compute=compute_75,code=sm_75 -gencode compute=compute_80,code=sm_80 -gencode compute=compute_86,code=sm_86 -gencode compute=compute_90,code=sm_90",
+        "gpus_per_node": 1,
+        "num_nodes": 1
+    },
+    "config": {
+        "adapter": {
+            "alpha": 16,
+            "bias_type": "none",
+            "dropout": 0.05,
+            "postprocessor": {
+                "merge_adapter_into_base_model": false,
+                "progressbar": false
+            },
+            "pretrained_adapter_weights": null,
+            "r": 8,
+            "target_modules": null,
+            "type": "lora",
+            "use_dora": false,
+            "use_rslora": false
+        },
+        "backend": null,
+        "base_model": "maritaca-ai/sabia-7b",
+        "defaults": {
+            "text": {
+                "decoder": {
+                    "fc_activation": "relu",
+                    "fc_bias_initializer": "zeros",
+                    "fc_dropout": 0.0,
+                    "fc_layers": null,
+                    "fc_norm": null,
+                    "fc_norm_params": null,
+                    "fc_output_size": 256,
+                    "fc_use_bias": true,
+                    "fc_weights_initializer": "xavier_uniform",
+                    "input_size": null,
+                    "max_new_tokens": null,
+                    "num_fc_layers": 0,
+                    "pretrained_model_name_or_path": "",
+                    "tokenizer": "hf_tokenizer",
+                    "type": "text_extractor",
+                    "vocab_file": ""
+                },
+                "encoder": {
+                    "skip": false,
+                    "type": "passthrough"
+                },
+                "loss": {
+                    "class_similarities": null,
+                    "class_similarities_temperature": 0,
+                    "class_weights": null,
+                    "confidence_penalty": 0,
+                    "robust_lambda": 0,
+                    "type": "next_token_softmax_cross_entropy",
+                    "unique": false,
+                    "weight": 1.0
+                },
+                "preprocessing": {
+                    "cache_encoder_embeddings": false,
+                    "compute_idf": false,
+                    "computed_fill_value": "<UNK>",
+                    "fill_value": "<UNK>",
+                    "lowercase": false,
+                    "max_sequence_length": 256,
+                    "missing_value_strategy": "fill_with_const",
+                    "most_common": 20000,
+                    "ngram_size": 2,
+                    "padding": "right",
+                    "padding_symbol": "<PAD>",
+                    "pretrained_model_name_or_path": null,
+                    "prompt": {
+                        "retrieval": {
+                            "index_name": null,
+                            "k": 0,
+                            "model_name": null,
+                            "type": null
+                        },
+                        "task": null,
+                        "template": null
+                    },
+                    "sequence_length": null,
+                    "tokenizer": "space_punct",
+                    "unknown_symbol": "<UNK>",
+                    "vocab_file": null
+                }
+            }
+        },
+        "generation": {
+            "bad_words_ids": null,
+            "begin_suppress_tokens": null,
+            "bos_token_id": null,
+            "diversity_penalty": 0.0,
+            "do_sample": true,
+            "early_stopping": false,
+            "encoder_repetition_penalty": 1.0,
+            "eos_token_id": null,
+            "epsilon_cutoff": 0.0,
+            "eta_cutoff": 0.0,
+            "exponential_decay_length_penalty": null,
+            "force_words_ids": null,
+            "forced_bos_token_id": null,
+            "forced_decoder_ids": null,
+            "forced_eos_token_id": null,
+            "guidance_scale": null,
+            "length_penalty": 1.0,
+            "max_length": 32,
+            "max_new_tokens": 200,
+            "max_time": null,
+            "min_length": 0,
+            "min_new_tokens": null,
+            "no_repeat_ngram_size": 0,
+            "num_beam_groups": 1,
+            "num_beams": 1,
+            "pad_token_id": null,
+            "penalty_alpha": null,
+            "prompt_lookup_num_tokens": null,
+            "remove_invalid_values": false,
+            "renormalize_logits": false,
+            "repetition_penalty": 1.0,
+            "sequence_bias": null,
+            "suppress_tokens": null,
+            "temperature": 0.001,
+            "top_k": 50,
+            "top_p": 1.0,
+            "typical_p": 1.0,
+            "use_cache": true
+        },
+        "hyperopt": null,
+        "input_features": [
+            {
+                "active": true,
+                "column": "input",
+                "encoder": {
+                    "skip": false,
+                    "type": "passthrough"
+                },
+                "name": "input",
+                "preprocessing": {
+                    "cache_encoder_embeddings": false,
+                    "compute_idf": false,
+                    "computed_fill_value": "<UNK>",
+                    "fill_value": "<UNK>",
+                    "lowercase": false,
+                    "max_sequence_length": null,
+                    "missing_value_strategy": "fill_with_const",
+                    "most_common": 20000,
+                    "ngram_size": 2,
+                    "padding": "left",
+                    "padding_symbol": "<PAD>",
+                    "pretrained_model_name_or_path": "maritaca-ai/sabia-7b",
+                    "sequence_length": null,
+                    "tokenizer": "hf_tokenizer",
+                    "unknown_symbol": "<UNK>",
+                    "vocab_file": null
+                },
+                "proc_column": "input_htcAoW",
+                "tied": null,
+                "type": "text"
+            }
+        ],
+        "ludwig_version": "0.10.2",
+        "model_parameters": null,
+        "model_type": "llm",
+        "output_features": [
+            {
+                "active": true,
+                "class_similarities": null,
+                "column": "output",
+                "decoder": {
+                    "fc_activation": "relu",
+                    "fc_bias_initializer": "zeros",
+                    "fc_dropout": 0.0,
+                    "fc_layers": null,
+                    "fc_norm": null,
+                    "fc_norm_params": null,
+                    "fc_output_size": 256,
+                    "fc_use_bias": true,
+                    "fc_weights_initializer": "xavier_uniform",
+                    "input_size": null,
+                    "max_new_tokens": 200,
+                    "num_fc_layers": 0,
+                    "pretrained_model_name_or_path": "maritaca-ai/sabia-7b",
+                    "tokenizer": "hf_tokenizer",
+                    "type": "text_extractor",
+                    "vocab_file": ""
+                },
+                "default_validation_metric": "loss",
+                "dependencies": [],
+                "input_size": null,
+                "loss": {
+                    "class_similarities": null,
+                    "class_similarities_temperature": 0,
+                    "class_weights": null,
+                    "confidence_penalty": 0,
+                    "robust_lambda": 0,
+                    "type": "next_token_softmax_cross_entropy",
+                    "unique": false,
+                    "weight": 1.0
+                },
+                "name": "output",
+                "num_classes": null,
+                "preprocessing": {
+                    "cache_encoder_embeddings": false,
+                    "compute_idf": false,
+                    "computed_fill_value": "<UNK>",
+                    "fill_value": "<UNK>",
+                    "lowercase": false,
+                    "max_sequence_length": null,
+                    "missing_value_strategy": "drop_row",
+                    "most_common": 20000,
+                    "ngram_size": 2,
+                    "padding": "left",
+                    "padding_symbol": "<PAD>",
+                    "pretrained_model_name_or_path": "maritaca-ai/sabia-7b",
+                    "sequence_length": null,
+                    "tokenizer": "hf_tokenizer",
+                    "unknown_symbol": "<UNK>",
+                    "vocab_file": null
+                },
+                "proc_column": "output_eqE4WW",
+                "reduce_dependencies": "sum",
+                "reduce_input": "sum",
+                "type": "text"
+            }
+        ],
+        "preprocessing": {
+            "global_max_sequence_length": null,
+            "oversample_minority": null,
+            "sample_ratio": 1.0,
+            "sample_size": null,
+            "split": {
+                "probabilities": [
+                    0.9,
+                    0.1,
+                    0.0
+                ],
+                "type": "random"
+            },
+            "undersample_majority": null
+        },
+        "prompt": {
+            "retrieval": {
+                "index_name": null,
+                "k": 0,
+                "model_name": null,
+                "type": null
+            },
+            "task": null,
+            "template": "### Instru\u00e7\u00e3o: Voc\u00ea receber\u00e1 o texto de uma reda\u00e7\u00e3o extra\u00edda por um sistema de OCR. Corrija os erros presentes no texto.\n### Entrada: {input}\n### Resposta:"
+        },
+        "quantization": {
+            "bits": 4,
+            "bnb_4bit_compute_dtype": "float16",
+            "bnb_4bit_quant_type": "nf4",
+            "bnb_4bit_use_double_quant": true,
+            "llm_int8_has_fp16_weight": false,
+            "llm_int8_threshold": 6.0
+        },
+        "trainer": {
+            "base_learning_rate": 0.0,
+            "batch_size": 1,
+            "bucketing_field": null,
+            "checkpoints_per_epoch": 0,
+            "compile": false,
+            "early_stop": 5,
+            "effective_batch_size": "auto",
+            "enable_gradient_checkpointing": false,
+            "enable_profiling": false,
+            "epochs": 1,
+            "eval_batch_size": 1,
+            "eval_steps": null,
+            "evaluate_training_set": false,
+            "gradient_accumulation_steps": 16,
+            "gradient_clipping": {
+                "clipglobalnorm": 0.5,
+                "clipnorm": null,
+                "clipvalue": null
+            },
+            "increase_batch_size_eval_metric": "loss",
+            "increase_batch_size_eval_split": "training",
+            "increase_batch_size_on_plateau": 0,
+            "increase_batch_size_on_plateau_patience": 5,
+            "increase_batch_size_on_plateau_rate": 2.0,
+            "learning_rate": 0.0001,
+            "learning_rate_scaling": "linear",
+            "learning_rate_scheduler": {
+                "decay": null,
+                "decay_rate": 0.96,
+                "decay_steps": 10000,
+                "eta_min": 0,
+                "reduce_eval_metric": "loss",
+                "reduce_eval_split": "training",
+                "reduce_on_plateau": 0,
+                "reduce_on_plateau_patience": 10,
+                "reduce_on_plateau_rate": 0.1,
+                "staircase": false,
+                "t_0": null,
+                "t_mult": 1,
+                "warmup_evaluations": 0,
+                "warmup_fraction": 0.03
+            },
+            "max_batch_size": 1099511627776,
+            "optimizer": {
+                "amsgrad": false,
+                "betas": [
+                    0.9,
+                    0.999
+                ],
+                "eps": 1e-08,
+                "type": "adam",
+                "weight_decay": 0.0
+            },
+            "profiler": {
+                "active": 3,
+                "repeat": 5,
+                "skip_first": 0,
+                "wait": 1,
+                "warmup": 1
+            },
+            "regularization_lambda": 0.0,
+            "regularization_type": "l2",
+            "should_shuffle": true,
+            "skip_all_evaluation": false,
+            "steps_per_checkpoint": 0,
+            "train_steps": null,
+            "type": "finetune",
+            "use_mixed_precision": false,
+            "validation_field": "output",
+            "validation_metric": "loss"
+        }
+    },
+    "data_format": "<class 'pandas.core.frame.DataFrame'>",
+    "ludwig_version": "0.10.2",
+    "random_seed": 42,
+    "torch_version": "2.1.2+cu121"
+}

sabia/model/model/logs/training/events.out.tfevents.1725791539.user-System-Product-Name.56936.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d38ca9f1839d303cce4c5c5dfd88769aeba741cbd6fb4c70b8af84607ce3ccf
+size 314339737

sabia/model/model/logs/validation/events.out.tfevents.1725791539.user-System-Product-Name.56936.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060bfa2b583d066fa6f5b530db229e893d60a094f37694d5c75fa3f3a1a07559
+size 478

sabia/model/model/model_weights/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: maritaca-ai/sabia-7b
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.0

sabia/model/model/model_weights/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "maritaca-ai/sabia-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

sabia/model/model/model_weights/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a306c0c2485e723376469ecb545d5217682ae39526956068af4a736a575619
+size 16794200

sabia/model/model/training_checkpoints/best.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a088cc61dd62ca5347c304b1e187461280751ef69de3c5ed642dfeb0e288891f
+size 50549798

sabia/model/model/training_checkpoints/latest.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a088cc61dd62ca5347c304b1e187461280751ef69de3c5ed642dfeb0e288891f
+size 50549798

sabia/model/model/training_progress.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe282a109a060ed490428f687c3436aef1b14f1ef9ca44d3b9446d5ebc3a094d
+size 10961981

sabia/model/training_statistics.json

@@ -0,0 +1,55 @@
+{
+    "evaluation_frequency": {
+        "frequency": 1,
+        "period": "epoch"
+    },
+    "test": {},
+    "training": {
+        "combined": {
+            "loss": [
+                0.2769858241081238
+            ]
+        },
+        "output": {
+            "loss": [
+                0.2769858241081238
+            ],
+            "next_token_perplexity": [
+                12867.28125
+            ],
+            "perplexity": [
+                31970.078125
+            ],
+            "sequence_accuracy": [
+                0.0
+            ],
+            "token_accuracy": [
+                0.00020247767679393291
+            ]
+        }
+    },
+    "validation": {
+        "combined": {
+            "loss": [
+                0.2222265750169754
+            ]
+        },
+        "output": {
+            "loss": [
+                0.2222265750169754
+            ],
+            "next_token_perplexity": [
+                12715.419921875
+            ],
+            "perplexity": [
+                31956.02734375
+            ],
+            "sequence_accuracy": [
+                0.0
+            ],
+            "token_accuracy": [
+                0.00017928318993654102
+            ]
+        }
+    }
+}

sabia/nohup.out

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812ef1a239c13ca702e4c914d9e0b7daac1553675b1b2b57853a12d9d3ea6cbb
+size 41945355