tokenizer minimized

config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e05eed608b1f296bbd16058c8eb4f265dc0cc6290f4b5b59afb1ffa3f02cbc
-size 8328624
+oid sha256:128b9d751ad0fa715a2a39758fc840b57167725b019cc13813d855933503a0dd
+size 142920

special_tokens_map.json

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

tokenizer_config.json

@@ -1,42 +1,58 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "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,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": false,
-  "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
+  "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]"
 }