Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,42 @@
+---
+library_name: transformers
+tags:
+- tokenizer
+- mlm
+license: mit
+---
+
+# claude tokenizer: mlm
+
+A variant of [Xenova/claude-tokenizer](https://huggingface.co/Xenova/claude-tokenizer) with some small changes to support usage as an MLM tokenizer.
+
+```py
+from transformers import AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained('pszemraj/claude-tokenizer-mlm')
+
+text = "Hello, this is a test input."
+ids = tokenizer(text)
+print(tokenizer.decode(ids['input_ids'], skip_special_tokens=False))
+# <bos>Hello, this is a test input.<EOT>
+len(tokenizer)
+# 65004
+```
+
+
+details relevant for model configs using this:
+```py
+>>> tokenizer
+GPT2TokenizerFast(name_or_path='pszemraj/claude-tokenizer-mlm', vocab_size=65000, model_max_length=200000, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<bos>', 'eos_token': '<EOT>', 'unk_token': '<EOT>', 'sep_token': '<EOT>', 'pad_token': '<pad>', 'cls_token': '<bos>', 'mask_token': '<mask>'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={
+        0: AddedToken("<EOT>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        1: AddedToken("<META>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        2: AddedToken("<META_START>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        3: AddedToken("<META_END>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        4: AddedToken("<SOS>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        65000: AddedToken("<pad>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        65001: AddedToken("<CLS>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        65002: AddedToken("<bos>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+        65003: AddedToken("<mask>", rstrip=False, lstrip=True, single_word=False, normalized=True, special=True),
+}
+```
+
+the `<CLS>` token is added but unused, both the CLS and BOS tokens are set to `<bos>` - see `tokenizer_config.json` for details

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<CLS>": 65001,
+  "<bos>": 65002,
+  "<mask>": 65003,
+  "<pad>": 65000
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<EOT>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<EOT>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<EOT>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,91 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<META>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<META_START>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<META_END>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<SOS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65001": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65002": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65003": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<bos>",
+  "eos_token": "<EOT>",
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_max_length": 200000,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "<EOT>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<EOT>"
+}