初始化项目，由ModelHub XC社区提供模型

Model: BUT-FIT/Czech-GPT-2-XL-133k Source: Original Platform
2026-06-10 21:21:30 +08:00
commit 309feb9219
10 changed files with 128024 additions and 0 deletions
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,34 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64001": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "[EOS]",
+  "model_max_length": 1024,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}