fix tokenization for chatml

config.json

@@ -20,6 +20,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.34.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32002
 }

tokenizer_config.json

@@ -1,5 +1,5 @@
 {
-  "add_bos_token": true,
+  "add_bos_token": false,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
@@ -32,28 +32,28 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "32001": {
       "content": "<|im_start|>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<|im_end|>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "tokenizer_file": "/workspace/data/huggingface-cache/hub/models--mistralai--Mistral-7B-v0.1/snapshots/ae9d75c6b4eb39515def78c685fb4d71d49fc2cf/tokenizer.json",
   "trust_remote_code": false,
   "unk_token": "<unk>",
   "use_default_system_prompt": true,