(Trained with Unsloth)

chat_template.jinja

@@ -1,15 +1,4 @@
-{% if 'role' in messages[0] %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user
-' + message['content'] + '<|im_end|>
-'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant
-' + message['content'] + '<|im_end|>
-' }}{% else %}{{ '<|im_start|>system
-' + message['content'] + '<|im_end|>
-' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
-' }}{% endif %}{% else %}{{ bos_token }}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user
-' + message['value'] + '<|im_end|>
-'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant
-' + message['value'] + '<|im_end|>
-' }}{% else %}{{ '<|im_start|>system
-' + message['value'] + '<|im_end|>
-' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
-' }}{% endif %}{% endif %}
+{{ bos_token }}{% 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 %}{% 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

@@ -1,6 +1,34 @@
 {
-  "bos_token": "<bos>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3bfe75911be2d16e407044cd3a130f770b0a690b4ab8dd63b583c716f68613b
-size 34356045
+oid sha256:b7eb818e7f83838615f7d3ca8b4f7690af124ce01dbf4870378d65aad732c22a
+size 34356140

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -11,7 +11,7 @@
       "special": true
     },
     "1": {
-      "content": "<|im_end|>",
+      "content": "<eos>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -851,7 +851,7 @@
       "special": false
     },
     "106": {
-      "content": "<|im_start|>",
+      "content": "<start_of_turn>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1739,16 +1739,20 @@
       "special": false
     }
   },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<eos>",
   "extra_special_tokens": {},
-  "max_length": 1024,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 8192,
   "pad_token": "<pad>",
-  "stride": 0,
-  "tokenizer_class": "GemmaTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }