Chat template and EOS (#1)

- Chat template and EOS (714b74719647699a0c9a89d7ecb6ce4691bdc992)


Co-authored-by: Djuunaa <[email protected]>

config.json

@@ -1,12 +1,17 @@
 {
-  "_name_or_path": "ZeroXClem/Llama3.1-Hermes3-SuperNova-8B-L3.1-Purosani-2-8B",
+  "_name_or_path": "unsloth/Meta-Llama-3.1-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -30,7 +35,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.45.1",
   "unsloth_version": "2024.9",
   "use_cache": true,
   "vocab_size": 128256

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

@@ -2050,14 +2050,16 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|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 %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
+  "eos_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|finetune_right_pad_id|>",
+  "pad_token": "<|eot_id|>",
   "padding_side": "left",
+  "split_special_tokens": false,
   "tokenizer_class": "PreTrainedTokenizerFast"
 }