Upload 3 files

tokenizer/special_tokens_map.json

@@ -1,21 +1,20 @@
 {
   "bos_token": {
-    "content": "<|startoftext|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
   "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,

tokenizer/tokenizer_config.json

@@ -1,33 +1,32 @@
 {
-  "add_prefix_space": false,
   "bos_token": {
     "__type": "AddedToken",
-    "content": "<|startoftext|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "clean_up_tokenization_spaces": true,
-  "do_lower_case": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": {
     "__type": "AddedToken",
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "errors": "replace",
-  "model_max_length": 77,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "CLIPTokenizer",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
   "unk_token": {
     "__type": "AddedToken",
-    "content": "<|endoftext|>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
-  }
+  },
+  "use_default_system_prompt": true
 }