Upload folder using huggingface_hub

README.md

@@ -0,0 +1,28 @@
+---
+library_name: transformers
+tags:
+ - transformers.js
+ - tokenizers
+---
+
+# text-embedding-ada-002 Tokenizer
+
+A 🤗-compatible version of the **text-embedding-ada-002 tokenizer** (adapted from [openai/tiktoken](https://github.com/openai/tiktoken)). This means it can be used with Hugging Face libraries including [Transformers](https://github.com/huggingface/transformers), [Tokenizers](https://github.com/huggingface/tokenizers), and [Transformers.js](https://github.com/xenova/transformers.js).
+
+## Example usage:
+
+### Transformers/Tokenizers
+```py
+from transformers import GPT2TokenizerFast
+
+tokenizer = GPT2TokenizerFast.from_pretrained('Xenova/text-embedding-ada-002')
+assert tokenizer.encode('hello world') == [15339, 1917]
+```
+
+### Transformers.js
+```js
+import { AutoTokenizer } from '@xenova/transformers';
+
+const tokenizer = await AutoTokenizer.from_pretrained('Xenova/text-embedding-ada-002');
+const tokens = tokenizer.encode('hello world'); // [15339, 1917]
+```

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "tokenizer_class": "GPT4Tokenizer",
+  "unk_token": "<|endoftext|>"
+}