Upload folder using huggingface_hub

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "sentence-transformers/distiluse-base-multilingual-cased-v1",
-  "activation": "gelu",
+  "_name_or_path": "allegro/herbert-base-cased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "optimism",
     "1": "anger",
@@ -15,23 +15,25 @@
     "3": "sadness"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "anger": 1,
     "joy": 2,
     "optimism": 0,
     "sadness": 3
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "tokenizer_class": "HerbertTokenizerFast",
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
-  "vocab_size": 119547
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e89e666006d22b690f4471fa8b34a6a9c7bd1628fd2cdb53c454fc0e901a672
-size 541346477
+oid sha256:e091b954db5d3da1a259fa39a6e3b52b198b320020d9ebe859a6b5ba8d251d44
+size 497856629

special_tokens_map.json

@@ -1,7 +1,8 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,16 +1,15 @@
 {
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
-  "max_len": 512,
+  "cls_token": "<s>",
+  "do_lowercase_and_remove_accent": false,
+  "id2lang": null,
+  "lang2id": null,
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "HerbertTokenizer",
+  "unk_token": "<unk>"
 }