Update generation_config.json (#7)

- Update generation_config.json (54c1c7e94228a64490ccb5d2f4ef26feae700e69)
- Update config.json (3ba643061a185aa53c7406b318a3715279f70bbd)
- Update tokenizer_config.json (979fafd58b04977de417e5e7c2cbd3cbb11ecdf5)


Co-authored-by: Yaowei Zheng <[email protected]>

config.json

@@ -21,7 +21,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.40.0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "eos_token_id": 128009,
   "transformers_version": "4.40.0"
 }

tokenizer_config.json

@@ -2050,16 +2050,14 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|>\\n\\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\\n\\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% set loop_messages = messages[1:] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message | trim + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
+  "pad_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|eot_id|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
   "tokenizer_class": "PreTrainedTokenizerFast"
 }