Downloads · 30 days
0
bpe_ltr_ind_Latn_32000_v2
flexitok/bpe_ltr_ind_Latn_32000_v2
bpe_ltr_ind_Latn_32000_v2 is a machine learning model from flexitok. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
A Byte-Level BPE tokenizer trained on indLatn data from Fineweb-2-HQ.
Access
Public
Updated Apr 15, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json3.3 MB · 86%
At a glance
- License
- mit
- Access
- Public
- Created
- Apr 14, 2026
- Updated
- Apr 15, 2026
- SHA
- 62153b0a
Model card
From the Hugging Face model README
Byte-Level BPE Tokenizer: ind_Latn (32K)
A Byte-Level BPE tokenizer trained on ind_Latn data from Fineweb-2-HQ.
Training Details
| Parameter | Value |
|---|---|
| Algorithm | Byte-Level BPE |
| Language | ind_Latn |
| Target Vocab Size | 32,000 |
| Final Vocab Size | 32,851 |
| Pre-tokenizer | custom:ind_Latn |
| Number handling | ltr_3digit |
| Contraction handling | True |
| Normalizer | NFC |
| Special Tokens | <s>, </s>, <pad>, <unk> |
| Training Shards | 2 |
Usage
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("flexitok/bpe_ltr_ind_Latn_32000_v2")
tokens = tokenizer.encode("Hello, world!")
Files
tokenizer.json— Full HuggingFace tokenizervocab.json— Vocabulary mappingmerges.txt— BPE merge rules
Sample Encoding
| Text | Tokens | Token IDs |
|---|---|---|
Hello, world! 12345 This is a test. こんにちは | H, ello, ,, Ġworld, !, Ġ, 123, 45, ĠThis, Ġis, Ġa, Ġtest, ., Ġ, ãģ, ĵ, ãĤ, ĵ, ãģ, « | 42, 15107, 14, 16817, 3, 223, 17069, 4529, 13915, 1153, 395, 7029, 16, 223, 9732, 244, 15716, 244, 9732, 107 |
- License
- mit
- Languages
- ind
- Created
- Apr 14, 2026
- Updated
- Apr 15, 2026