Upload folder using huggingface_hub

config.json

@@ -30,7 +30,7 @@
   "problem_type": "single_label_classification",
   "tokenizer_class": "HerbertTokenizerFast",
   "torch_dtype": "float32",
-  "transformers_version": "4.24.0",
+  "transformers_version": "4.30.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 50000

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 n i
 i e
 o w

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69531b97a52063b95b79a9d2ded7cdc484c8fce2fec67b47db4037d12a1cc80
+oid sha256:2c1d537a9684fe66625e890daa350f51c428027ea36c99e110c64a59e9b4626f
 size 497853557

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 1,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,
@@ -95,6 +81,7 @@
     "continuing_subword_prefix": null,
     "end_of_word_suffix": "</w>",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

tokenizer_config.json

@@ -1,16 +1,15 @@
 {
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "do_lowercase_and_remove_accent": false,
   "id2lang": null,
   "lang2id": null,
   "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "allegro/herbert-base-cased",
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "special_tokens_map_file": "/home/mpogoda/.cache/huggingface/hub/models--allegro--herbert-base-cased/snapshots/50e33e0567be0c0b313832314c586e3df0dc2297/special_tokens_map.json",
   "tokenizer_class": "HerbertTokenizer",
   "unk_token": "<unk>"
 }