Upload tokenizer

special_tokens_map.json

@@ -1,23 +1,20 @@
 {
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "eos_token": {
-    "content": "</s>",
-    "lstrip": true,
+    "content": "<|im_end|>",
+    "lstrip": false,
     "normalized": false,
-    "rstrip": true,
+    "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
-    "lstrip": true,
+    "content": "<|endoftext|>",
+    "lstrip": false,
     "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
+    "rstrip": false,
     "single_word": false
   }
 }

tokenizer_config.json

@@ -1,33 +1,52 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "1": {
-      "content": "</s>",
-      "lstrip": true,
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "<unk>",
-      "lstrip": true,
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "clean_up_tokenization_spaces": true,
-  "do_lower_case": true,
-  "eos_token": "</s>",
-  "model_input_names": [
-    "input_ids"
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
   ],
-  "model_max_length": 64,
-  "pad_token": "</s>",
-  "processor_class": "SiglipProcessor",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "SiglipTokenizer",
-  "unk_token": "<unk>"
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }