RioShiina commited on
Commit
ad0e49f
1 Parent(s): f58a0c4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -0
README.md CHANGED
@@ -1,3 +1,34 @@
1
  ---
2
  license: llama2
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: llama2
3
+ language:
4
+ - ja
5
+ - en
6
+ base_model: tokyotech-llm/Swallow-70b-instruct-hf
7
+ pipeline_tag: text-generation
8
  ---
9
+
10
+ **[2.2bpw](https://huggingface.co/rioshiina/Swallow-70b-instruct-exl2/tree/4.0bpw)** (high quality loss, only for 24GB vRAM test.)
11
+ **[4.0bpw](https://huggingface.co/rioshiina/Swallow-70b-instruct-exl2/tree/4.0bpw)**
12
+ **[6.0bpw](https://huggingface.co/rioshiina/Swallow-70b-instruct-exl2/tree/6.0bpw)**
13
+ **[8.0bpw](https://huggingface.co/rioshiina/Swallow-70b-instruct-exl2/tree/8.0bpw)**
14
+
15
+ # Swallow-70b-instruct-exl2
16
+ - Model creator: [tokyotech-llm](https://huggingface.co/tokyotech-llm)
17
+ - Original model: [Swallow-70b-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-hf)
18
+
19
+ ## Prompt template
20
+
21
+ ```
22
+ ### 指示:
23
+ {instruction}
24
+
25
+ ### 入力:
26
+ {input}
27
+
28
+ ### 応答:
29
+
30
+ ```
31
+
32
+ ### Licence
33
+
34
+ Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.