Upload folder using huggingface_hub
Browse files- README.md +42 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- arb
|
| 5 |
+
tags:
|
| 6 |
+
- tokenizer
|
| 7 |
+
- unigram
|
| 8 |
+
- flexitok
|
| 9 |
+
- fineweb2
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# UnigramLM Tokenizer: arb_Arab (8K)
|
| 13 |
+
|
| 14 |
+
A **UnigramLM** tokenizer trained on **arb_Arab** data from Fineweb-2-HQ.
|
| 15 |
+
|
| 16 |
+
## Training Details
|
| 17 |
+
|
| 18 |
+
| Parameter | Value |
|
| 19 |
+
|-----------|-------|
|
| 20 |
+
| Algorithm | UnigramLM |
|
| 21 |
+
| Language | `arb_Arab` |
|
| 22 |
+
| Target Vocab Size | 8,000 |
|
| 23 |
+
| Final Vocab Size | 8,000 |
|
| 24 |
+
| Pre-tokenizer | ByteLevel |
|
| 25 |
+
| Normalizer | NFC |
|
| 26 |
+
| Special Tokens | `<s>`, `</s>`, `<pad>`, `<unk>` |
|
| 27 |
+
| Training Shards | 2 |
|
| 28 |
+
|
| 29 |
+
## Usage
|
| 30 |
+
|
| 31 |
+
```python
|
| 32 |
+
from transformers import AutoTokenizer
|
| 33 |
+
|
| 34 |
+
tokenizer = AutoTokenizer.from_pretrained("flexitok/-unigram_arb_Arab_8000")
|
| 35 |
+
tokens = tokenizer.encode("Hello, world!")
|
| 36 |
+
```
|
| 37 |
+
|
| 38 |
+
## Files
|
| 39 |
+
|
| 40 |
+
- `tokenizer.json` — Full HuggingFace tokenizer
|
| 41 |
+
- `vocab.json` — Vocabulary mapping
|
| 42 |
+
- `tokenizer.model` — SentencePiece protobuf (if available)
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce872f542e30e3069ea3a76e982012b8e5c009563acdc4027ee4fe865a83f02e
|
| 3 |
+
size 215603
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<pad>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"clean_up_tokenization_spaces": false,
|
| 38 |
+
"eos_token": "</s>",
|
| 39 |
+
"extra_special_tokens": {},
|
| 40 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
+
"pad_token": "<pad>",
|
| 42 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 43 |
+
"unk_token": "<unk>"
|
| 44 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|