Update languages and fix
Browse files
README.md
CHANGED
|
@@ -1,16 +1,48 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
language:
|
| 4 |
-
-
|
| 5 |
-
-
|
| 6 |
-
-
|
| 7 |
-
-
|
| 8 |
-
-
|
| 9 |
-
-
|
| 10 |
-
-
|
| 11 |
-
-
|
| 12 |
-
-
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
# OpenEuroLLM Tokenizer v2 (oellm-262k-v2)
|
|
@@ -64,10 +96,10 @@ print(f"Encoded token IDs: {encoded_ids}")
|
|
| 64 |
|
| 65 |
decoded_text = tokenizer.decode(encoded_ids)
|
| 66 |
print(f"Decoded text: {decoded_text}")
|
| 67 |
-
```
|
| 68 |
|
| 69 |
# The tokenizer automatically adds a BOS token
|
| 70 |
# >>> Decoded text: <s> Hej, detta är ett test av den nya OpenEuroLLM-tokeniseraren.
|
|
|
|
| 71 |
|
| 72 |
## Intended Use and Limitations
|
| 73 |
This tokenizer is intended to be used for pre-training and fine-tuning large language models
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
language:
|
| 4 |
+
- als
|
| 5 |
+
- bos
|
| 6 |
+
- bul
|
| 7 |
+
- cat
|
| 8 |
+
- ces
|
| 9 |
+
- dan
|
| 10 |
+
- deu
|
| 11 |
+
- ekk
|
| 12 |
+
- ell
|
| 13 |
+
- eng
|
| 14 |
+
- est
|
| 15 |
+
- eus
|
| 16 |
+
- fin
|
| 17 |
+
- fra
|
| 18 |
+
- gle
|
| 19 |
+
- glg
|
| 20 |
+
- hrv
|
| 21 |
+
- hun
|
| 22 |
+
- isl
|
| 23 |
+
- ita
|
| 24 |
+
- kat
|
| 25 |
+
- lav
|
| 26 |
+
- lit
|
| 27 |
+
- ltg
|
| 28 |
+
- lvs
|
| 29 |
+
- mkd
|
| 30 |
+
- mlt
|
| 31 |
+
- nld
|
| 32 |
+
- nno
|
| 33 |
+
- nob
|
| 34 |
+
- nor
|
| 35 |
+
- pol
|
| 36 |
+
- por
|
| 37 |
+
- ron
|
| 38 |
+
- slk
|
| 39 |
+
- slv
|
| 40 |
+
- spa
|
| 41 |
+
- sqi
|
| 42 |
+
- srp
|
| 43 |
+
- swe
|
| 44 |
+
- tur
|
| 45 |
+
- ukr
|
| 46 |
---
|
| 47 |
|
| 48 |
# OpenEuroLLM Tokenizer v2 (oellm-262k-v2)
|
|
|
|
| 96 |
|
| 97 |
decoded_text = tokenizer.decode(encoded_ids)
|
| 98 |
print(f"Decoded text: {decoded_text}")
|
|
|
|
| 99 |
|
| 100 |
# The tokenizer automatically adds a BOS token
|
| 101 |
# >>> Decoded text: <s> Hej, detta är ett test av den nya OpenEuroLLM-tokeniseraren.
|
| 102 |
+
```
|
| 103 |
|
| 104 |
## Intended Use and Limitations
|
| 105 |
This tokenizer is intended to be used for pre-training and fine-tuning large language models
|