fast llama tokenizer

config.json

@@ -26,5 +26,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.1",
   "use_cache": true,
-  "vocab_size": 25
+  "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128b9d751ad0fa715a2a39758fc840b57167725b019cc13813d855933503a0dd
-size 142920
+oid sha256:ce086d93d685cbfd962b5517f44d739122c1478d294ec51e8853ad0be1ef80d4
+size 8328624

special_tokens_map.json

@@ -1,50 +1,22 @@
 {
   "bos_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "[UNK]",
+    "content": "<unk>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -1,58 +1,41 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
-      "content": "[UNK]",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "[CLS]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "[SEP]",
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "[CLS]",
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "max_length": 10,
-  "model_max_length": 10,
-  "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "[SEP]",
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "[UNK]"
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }