BPE 16k tokenizer, Italian-first bilingual with ChatML

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ]
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 4096,
+  "chat_template": "{% for message in messages %}<|im_start|>{{ message['role'] }}\n{{ message['content'] }}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "add_bos_token": false,
+  "add_eos_token": false
+}