AXIOM-1 tokenizer
Browse files- README.md +8 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
README.md
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# AXIOM-1 Tokenizer
|
| 2 |
+
|
| 3 |
+
Tokenizador BPE byte-level (32K) entrenado desde cero para AXIOM-1. Vocabulario propio — soberanía total.
|
| 4 |
+
|
| 5 |
+
- vocab_size: 32000
|
| 6 |
+
- contexto: 512 tokens
|
| 7 |
+
|
| 8 |
+
Uso: `AutoTokenizer.from_pretrained("evox-os/axiom-1-tokenizer")`
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|