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 +1,90 @@
+---
+datasets:
+- BEE-spoke-data/bees-internal
+language:
+- en
+license: apache-2.0
+---
+
+# BeeTokenizer
+
+> note: this is **literally** a tokenizer trained on beekeeping text
+
+After minutes of hard work, it is now available.
+
+
+```python
+from transformers import AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained("BEE-spoke-data/BeeTokenizer")
+
+test_string = "When dealing with Varroa destructor mites, it's crucial to administer the right acaricides during the late autumn months, but only after ensuring that the worker bee population is free from pesticide contamination."
+
+output = tokenizer(test_string)
+print(f"Test string: {test_string}")
+print(f"Tokens ({len(output.input_ids)}):\n\t{output.input_ids}")
+```
+
+
+## Notes
+
+1. the default tokenizer (on branch `main`) has a vocab size of 32000
+2. based on the `SentencePieceBPETokenizer` class 
+
+<details>
+  <summary>How to Tokenize Text and Retrieve Offsets</summary>
+  
+  To tokenize a complex sentence and also retrieve the offsets mapping, you can use the following Python code snippet:
+
+  ```python
+  from transformers import AutoTokenizer
+
+  # Initialize the tokenizer
+  tokenizer = AutoTokenizer.from_pretrained("BEE-spoke-data/BeeTokenizer")
+
+  # Sample complex sentence related to beekeeping
+  test_string = "When dealing with Varroa destructor mites, it's crucial to administer the right acaricides during the late autumn months, but only after ensuring that the worker bee population is free from pesticide contamination."
+
+  # Tokenize the input string and get the offsets mapping
+  output = tokenizer.encode_plus(test_string, return_offsets_mapping=True)
+
+  print(f"Test string: {test_string}")
+
+  # Tokens
+  tokens = tokenizer.convert_ids_to_tokens(output['input_ids'])
+  print(f"Tokens: {tokens}")
+
+  # Offsets
+  offsets = output['offset_mapping']
+  print(f"Offsets: {offsets}")
+  ```
+
+  This should result in the following (_Feb '24 version_):
+  
+  ```
+  >>> print(f"Test string: {test_string}")
+  Test string: When dealing with Varroa destructor mites, it's crucial to administer the right acaricides during the late autumn months, but only after ensuring that the worker bee population is free from pesticide contamination.
+  >>>
+  >>> # Tokens
+  >>> tokens = tokenizer.convert_ids_to_tokens(output['input_ids'])
+  >>> print(f"Tokens: {tokens}")
+  Tokens: ['When', '▁dealing', '▁with', '▁Varroa', '▁destructor', '▁mites,', "▁it's", '▁cru', 'cial', '▁to', '▁administer', '▁the', '▁right', '▁acar', 'icides', '▁during', '▁the', '▁late', '▁autumn', '▁months,', '▁but', '▁only', '▁after', '▁ensuring', '▁that', '▁the', '▁worker', '▁bee', '▁population', '▁is', '▁free', '▁from', '▁pesticide', '▁contam', 'ination.']
+  >>>
+  >>> # Offsets
+  >>> offsets = output['offset_mapping']
+  >>> print(f"Offsets: {offsets}")
+  Offsets: [(0, 4), (4, 12), (12, 17), (17, 24), (24, 35), (35, 42), (42, 47), (47, 51), (51, 55), (55, 58), (58, 69), (69, 73), (73, 79), (79, 84), (84, 90), (90, 97), (97, 101), (101, 106), (106, 113), (113, 121), (121, 125), (125, 130), (130, 136), (136, 145), (145, 150), (150, 154), (154, 161), (161, 165), (165, 176), (176, 179), (179, 184), (184, 189), (189, 199), (199, 206), (206, 214)]
+  ```
+
+  if you compare this to the output of [the llama tokenizer](https://huggingface.co/fxmarty/tiny-llama-fast-tokenizer) (below), you can quickly see which is more suited for beekeeping related language modeling.
+
+  ```
+  >>> print(f"Test string: {test_string}")
+  Test string: When dealing with Varroa destructor mites, it's crucial to administer the right acaricides during the late autumn months, but only after ensuring that the worker bee population is free from pesticide contamination.
+  >>> # Tokens
+  >>> tokens = tokenizer.convert_ids_to_tokens(output['input_ids'])
+  >>> print(f"Tokens: {toke>>> print(f"Tokens: {tokens}")
+  Tokens: ['<s>', '▁When', '▁dealing', '▁with', '▁Var', 'ro', 'a', '▁destruct', 'or', '▁mit', 'es', ',', '▁it', "'", 's', '▁cru', 'cial', '▁to', '▁admin', 'ister', '▁the', '▁right', '▁ac', 'ar', 'ic', 'ides', '▁during', '▁the', '▁late', '▁aut', 'umn', '▁months', ',', '▁but', '▁only', '▁after', '▁ens', 'uring', '▁that', '▁the', '▁worker', '▁be', 'e', '▁population', '▁is', '▁free', '▁from', '▁p', 'estic', 'ide', '▁cont', 'am', 'ination', '.']
+  >>> offsets = output['offset_mapping']
+  >>> print(f"Offsets: {offsets}")
+  Offsets: [(0, 0), (0, 4), (4, 12), (12, 17), (17, 21), (21, 23), (23, 24), (24, 33), (33, 35), (35, 39), (39, 41), (41, 42), (42, 45), (45, 46), (46, 47), (47, 51), (51, 55), (55, 58), (58, 64), (64, 69), (69, 73), (73, 79), (79, 82), (82, 84), (84, 86), (86, 90), (90, 97), (97, 101), (101, 106), (106, 110), (110, 113), (113, 120), (120, 121), (121, 125), (125, 130), (130, 136), (136, 140), (140, 145), (145, 150), (150, 154), (154, 161), (161, 164), (164, 165), (165, 176), (176, 179), (179, 184), (184, 189), (189, 191), (191, 196), (196, 199), (199, 204), (204, 206), (206, 213), (213, 214)]
+  ```

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,294 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31972": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31973": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31974": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31975": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31976": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31977": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31978": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31979": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31980": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31981": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31982": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31983": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31984": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31985": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31986": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31987": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31988": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31989": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31990": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31991": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31992": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31993": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31994": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31995": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31996": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31997": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31998": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31999": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "eos_token": "<|endoftext|>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}