初始化项目，由ModelHub XC社区提供模型

Model: minishlab/potion-base-32M Source: Original Platform
2026-05-14 12:54:03 +08:00
commit d3aa9c396a
10 changed files with 126550 additions and 0 deletions
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,55 @@
+{
+    "added_tokens_decoder": {
+        "0": {
+            "content": "[PAD]",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "1": {
+            "content": "[UNK]",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "2": {
+            "content": "[CLS]",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "3": {
+            "content": "[SEP]",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "4": {
+            "content": "[MASK]",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "clean_up_tokenization_spaces": true,
+    "cls_token": "[CLS]",
+    "do_lower_case": true,
+    "mask_token": "[MASK]",
+    "model_max_length": 1000000,
+    "pad_token": "[PAD]",
+    "sep_token": "[SEP]",
+    "strip_accents": null,
+    "tokenize_chinese_chars": true,
+    "tokenizer_class": "BertTokenizer",
+    "unk_token": "[UNK]"
+}