Initial commit: Uploading tokenizer directory

README.md

@@ -0,0 +1,29 @@
+# ArlowGPT Tokenizer
+
+This repository contains a custom-trained BPE tokenizer for ArlowGPT, created by Yuchen Xie.
+
+## Tokenizer Details
+
+- Type: BPE (Byte-Pair Encoding)
+- Vocabulary Size: 131,072 tokens
+- Special Tokens:
+  - Start of Text: <|startoftext|>
+  - End of Text: <|endoftext|>
+  - Padding: <|pad|>
+  - Unknown: <|unk|>
+  - Mask: <|mask|>
+  - Message Start: <|im_start|>
+  - Message End: <|im_end|>
+
+## Usage
+
+```python
+from transformers import PreTrainedTokenizerFast
+
+tokenizer = PreTrainedTokenizerFast.from_pretrained("yuchenxie/arlowgpt-tokenizer-v2")
+```
+
+## Training Details
+
+This tokenizer was trained on the FineWeb dataset using the Hugging Face tokenizers library.
+        

special_tokens_map.json

@@ -0,0 +1,53 @@
+{
+    "bos_token": {
+        "content": "<|startoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "eos_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "pad_token": {
+        "content": "<|pad|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "unk_token": {
+        "content": "<|unk|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "mask_token": {
+        "content": "<|mask|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "additional_special_tokens": [
+        {
+            "content": "<|im_start|>",
+            "single_word": false,
+            "lstrip": false,
+            "rstrip": false,
+            "normalized": true
+        },
+        {
+            "content": "<|im_end|>",
+            "single_word": false,
+            "lstrip": false,
+            "rstrip": false,
+            "normalized": true
+        }
+    ]
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+    "add_bos_token": false,
+    "add_eos_token": false,
+    "bos_token": "<|startoftext|>",
+    "clean_up_tokenization_spaces": true,
+    "eos_token": "<|endoftext|>",
+    "mask_token": "<|mask|>",
+    "model_max_length": 2048,
+    "pad_token": "<|pad|>",
+    "tokenizer_class": "PreTrainedTokenizerFast",
+    "unk_token": "<|unk|>",
+    "chat_template": "{% for message in messages %}{{'<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+    "model_input_names": ["input_ids", "attention_mask"],
+    "use_fast": true,
+    "name_or_path": "./tokenizer.json",
+    "tokenizer_type": "bpe",
+    "auto_map": {
+        "AutoTokenizer": ["tokenizers.Tokenizer", null]
+    },
+    "system_prompt": "You are ArlowGPT, an AI assistant created by Yuchen Xie. You aim to be helpful, honest, and direct in your interactions while maintaining high ethical standards.",
+    "padding_side": "right"
+}