Upload folder using huggingface_hub

added_tokens.json

@@ -2,6 +2,7 @@
   "<|assistant|>": 32001,
   "<|endoftext|>": 32000,
   "<|end|>": 32007,
+  "<|pad|>": 32011,
   "<|placeholder1|>": 32002,
   "<|placeholder2|>": 32003,
   "<|placeholder3|>": 32004,

special_tokens_map.json

@@ -7,14 +7,14 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|pad|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 4096,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 4096
+    },
+    "direction": "Left",
+    "pad_to_multiple_of": null,
+    "pad_id": 32011,
+    "pad_type_id": 0,
+    "pad_token": "<|pad|>"
+  },
   "added_tokens": [
     {
       "id": 0,
@@ -98,7 +112,7 @@
       "content": "<|end|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": true,
+      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -128,6 +142,15 @@
       "rstrip": true,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32011,
+      "content": "<|pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -87,7 +87,7 @@
       "content": "<|end|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -114,16 +114,24 @@
       "rstrip": true,
       "single_word": false,
       "special": true
+    },
+    "32011": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<s>",
   "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|end|>",
   "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 4096,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
   "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",