Suggested tokenizer changes by Unsloth.ai (#21)

- fix(root): Adds proposed changes by unsloth.ai. (b15fb484864f7247bfec0860d31e105173e809c7)
- chore(root): Changes pad_token to <|dummy_85|>. (492fc706206120688c0cc9d538e6be3ad6558f7f)

config.json

@@ -8,7 +8,7 @@
   "auto_map": {},
   "bos_token_id": 100257,
   "embd_pdrop": 0.0,
-  "eos_token_id": 100257,
+  "eos_token_id": 100265,
   "hidden_act": "silu",
   "hidden_size": 5120,
   "initializer_range": 0.02,
@@ -19,7 +19,7 @@
   "num_hidden_layers": 40,
   "num_key_value_heads": 10,
   "original_max_position_embeddings": 16384,
-  "pad_token_id": 100257,
+  "pad_token_id": 100349,
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

generation_config.json

@@ -1,9 +1,7 @@
 {
     "_from_model_config": true,
     "bos_token_id": 100257,
-    "eos_token_id": [
-      100257,
-      100265
-    ],
+    "eos_token_id": 100265,
+    "pad_token_id": 100349,
     "transformers_version": "4.47.0"
 }

special_tokens_map.json

@@ -1,5 +1,5 @@
 {
   "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>"
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|dummy_85|>"
 }

tokenizer_config.json

@@ -771,10 +771,10 @@
     }
   },
   "bos_token": "<|endoftext|>",
-  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|><|im_start|>assistant<|im_sep|>'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}",
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "model_max_length": 16384,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|dummy_85|>",
   "tokenizer_class": "GPT2Tokenizer"
 }