Update README.md
Browse files
README.md
CHANGED
@@ -7,6 +7,13 @@ license: llama2
|
|
7 |
tags:
|
8 |
- translation
|
9 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
# webbigdata/ALMA-7B-Ja-V2-GPTQ-Ja-En
|
11 |
|
12 |
ALMA-7B-Ja-V2は日本語から英語、英語から日本語への機械翻訳を行うモデルです。
|
|
|
7 |
tags:
|
8 |
- translation
|
9 |
---
|
10 |
+
|
11 |
+
# New Translation model released.
|
12 |
+
|
13 |
+
[C3TR-Adapter](https://huggingface.co/webbigdata/C3TR-Adapter) is the QLoRA adapter for google/gemma-7b.
|
14 |
+
Despite the 4-bit quantization, the memory GPU requirement has increased to 8.1 GB.
|
15 |
+
However, it is possible to run it with the free version of Colab and the performance is much improved!
|
16 |
+
|
17 |
# webbigdata/ALMA-7B-Ja-V2-GPTQ-Ja-En
|
18 |
|
19 |
ALMA-7B-Ja-V2は日本語から英語、英語から日本語への機械翻訳を行うモデルです。
|