Upload folder using huggingface_hub

special_tokens_map.json

@@ -1,27 +1,27 @@
 {
   "bos_token": {
-    "content": "<[BOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+    "content": "<[begin▁of▁sentence]>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<[EOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+    "content": "<[end▁of▁sentence]>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<[PAD_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+    "content": "<[PAD▁TOKEN]>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "<[SEP_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+    "content": "<[SEP▁TOKEN]>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5a7581f9bd555b11181c8fd69e9c7e6f6f5904d958f7c8771393aec7de1da9
-size 11892194
+oid sha256:db6520146c388c495a98bbea62ff6d00c0a8935bed33622e33bb33ec71aaafed
+size 11891696

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<[BOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+      "content": "<[begin▁of▁sentence]>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<[PAD_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+      "content": "<[PAD▁TOKEN]>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "<[EOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+      "content": "<[end▁of▁sentence]>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -49,7 +49,7 @@
       "special": true
     },
     "6": {
-      "content": "<[SEP_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+      "content": "<[SEP▁TOKEN]>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -993,7 +993,7 @@
       "special": true
     },
     "124": {
-      "content": "<[PLHD124_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+      "content": "<[fim-prefix]>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1001,7 +1001,7 @@
       "special": true
     },
     "125": {
-      "content": "<[PLHD125_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+      "content": "<[fim-suffix]>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1009,7 +1009,7 @@
       "special": true
     },
     "126": {
-      "content": "<[PLHD126_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+      "content": "<[fim-middle]>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1025,12 +1025,12 @@
       "special": true
     }
   },
-  "bos_token": "<[BOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+  "bos_token": "<[begin▁of▁sentence]>",
   "chat_template": "{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set role = message['role'] %}{{ bos_token + role + '\n' + message['content'] | trim + eos_token }}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<[EOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+  "eos_token": "<[end▁of▁sentence]>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<[PAD_never_used_51bce0c785ca2f68081bfa7d91973934]>",
-  "sep_token": "<[SEP_never_used_51bce0c785ca2f68081bfa7d91973934]>",
+  "pad_token": "<[PAD▁TOKEN]>",
+  "sep_token": "<[SEP▁TOKEN]>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }