Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- NTQAI/chatntq-ja-7b-v1.0
|
4 |
+
- Elizezen/Antler-7B
|
5 |
+
language:
|
6 |
+
- ja
|
7 |
+
tags:
|
8 |
+
- mistral
|
9 |
+
- mixtral
|
10 |
+
- merge
|
11 |
+
- moe
|
12 |
+
- not-for-all-audiences
|
13 |
+
- nsfw
|
14 |
+
pipeline_tag: text-generation
|
15 |
+
---
|
16 |
+
|
17 |
+
**[4.0bpw](https://huggingface.co/rioshiina/LightChatAssistant-2x7B-exl2/tree/4.0bpw)**
|
18 |
+
**[6.0bpw](https://huggingface.co/rioshiina/LightChatAssistant-2x7B-exl2/tree/6.0bpw)**
|
19 |
+
**[8.0bpw](https://huggingface.co/rioshiina/LightChatAssistant-2x7B-exl2/tree/8.0bpw)**
|
20 |
+
|
21 |
+
これは、[Sdff-Ltba](https://huggingface.co/Sdff-Ltba)さんの[LightChatAssistant-2x7B](https://huggingface.co/Sdff-Ltba/LightChatAssistant-2x7B)モデルをexl2量子化したものです。
|
22 |
+
Q4 cacheモードによる、32kのContextSize対応、8.0bpw量子化でVRAM16GBでフルロード可能です。
|