Update tokenizer

README.md

@@ -1,6 +1,6 @@
 ---
-datasets: wikitext
 license: other
+datasets: wikitext
 license_link: https://llama.meta.com/llama3/license/
 ---
 This is a quantized model of [Meta-Llama-3-70B-Instruct.yaml](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct.yaml) using GPTQ developed by [IST Austria](https://ist.ac.at/en/research/alistarh-group/)

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|end_of_text|>",
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -2052,7 +2052,7 @@
   "bos_token": "<|begin_of_text|>",
   "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
+  "eos_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"