update eos token (#6)

- update eos token (a99e713e7f1ca41418d981bb0f8d0f38f1704911)
- update eos token id in config.json (df3417bf36d3edcc1fadca30f8724da22acf7ef9)
- correct eos token in special token map (f239207f101efffb4cd3e5f86a425717e3ee227a)


Co-authored-by: Praful Mohanan <[email protected]>

config.json

@@ -6,7 +6,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "eos_token_id": 128009,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,

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 %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
+  "eos_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"