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 100 tokens to
|
| 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.)
|
|
@@ -22,7 +22,7 @@ Swallow-hf-13bの高い日本語力を利用した翻訳モデルです
|
|
| 22 |
[tokyotech-llm/Swallow-hf-13b](https://huggingface.co/tokyotech-llm/Swallow-13b-hf)
|
| 23 |
|
| 24 |
英日翻訳メインに、ファインチューニングしています
|
| 25 |
-
|
| 26 |
|
| 27 |
英語以外の言語から日本語への翻訳も一部対応しています
|
| 28 |
|
|
|
|
| 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 1-2 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.)
|
|
|
|
| 22 |
[tokyotech-llm/Swallow-hf-13b](https://huggingface.co/tokyotech-llm/Swallow-13b-hf)
|
| 23 |
|
| 24 |
英日翻訳メインに、ファインチューニングしています
|
| 25 |
+
1-2K tokenまでの翻訳に対応しています
|
| 26 |
|
| 27 |
英語以外の言語から日本語への翻訳も一部対応しています
|
| 28 |
|