aixsatoshi
commited on
Commit
•
e94b411
1
Parent(s):
8d536e1
Update README.md
Browse files
README.md
CHANGED
@@ -6,7 +6,7 @@ license: llama2
|
|
6 |
|
7 |
This is a translation model utilizing the high Japanese proficiency of Swallow-hf-13b, primarily focused on English-Japanese or any language-to-Japanese translation.
|
8 |
|
9 |
-
The model, tokyotech-llm/Swallow-13b-hf, has been fine-tuned with an 4K context and is mainly aimed at translating relatively long texts ranging from
|
10 |
|
11 |
While its core strength lies in English-Japanese translation, it also partially supports translation in other languages.
|
12 |
(Multilingual translation features and long context translation become unstable when quantized.)
|
|
|
6 |
|
7 |
This is a translation model utilizing the high Japanese proficiency of Swallow-hf-13b, primarily focused on English-Japanese or any language-to-Japanese translation.
|
8 |
|
9 |
+
The model, tokyotech-llm/Swallow-13b-hf, has been fine-tuned with an 4K context and is mainly aimed at translating relatively long texts ranging from 100 tokens to several thousand tokens.
|
10 |
|
11 |
While its core strength lies in English-Japanese translation, it also partially supports translation in other languages.
|
12 |
(Multilingual translation features and long context translation become unstable when quantized.)
|