Upload processor

chat_template.jinja

@@ -1,5 +1,4 @@
-{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '
-' }}{% if message['content'] is string %}{{ message['content'] }}{% else %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>
-' }}{% endfor %}{# Render all text next #}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{% endif %}{{ '<|im_end|>' + '
-' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
-' }}{% endif %}
+{{ bos_token }}{% for message in messages %}{% if message['role'] == 'assistant' %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}<start_of_turn>{{ role }}
+{{ message['content'] | trim }}<end_of_turn>
+{% endfor %}{% if add_generation_prompt %}<start_of_turn>model
+{% endif %}

special_tokens_map.json

@@ -3,8 +3,20 @@
     "<start_of_turn>",
     "<end_of_turn>"
   ],
-  "bos_token": "<|im_start|>",
-  "eos_token": "<|im_end|>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d0799ced231dd489d7946291b0ffc36aede4ec352cfb98c7ae1555f55874ab
-size 34362989
+oid sha256:c4b297c2611e679fa3ad2e8e77a7894870338ee92c2bbfbeff2d5b65496c47fd
+size 34363057

tokenizer_config.json

@@ -1,5 +1,5 @@
 {
-  "add_bos_token": false,
+  "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
@@ -2001,31 +2001,15 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "256001": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "256002": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
     "<start_of_turn>",
     "<end_of_turn>"
   ],
-  "bos_token": "<|im_start|>",
+  "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<end_of_turn>",
   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<unk>",
@@ -2033,7 +2017,7 @@
   "processor_class": "LlavaNextProcessor",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "tokenizer_class": "GemmaTokenizer",
+  "tokenizer_class": "GemmaTokenizerFast",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }