Kooten commited on
Commit
4bff5af
1 Parent(s): efbd875

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -7,6 +7,18 @@ Exllama 2 quant of [NeverSleep/Nethena-13B](https://huggingface.co/NeverSleep/Ne
7
 
8
  3 BPW, Head bit set to 8
9
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ## VRAM
11
  My VRAM usage with 13B models are:
12
  | Bits per weight | Context | VRAM |
@@ -20,15 +32,3 @@ My VRAM usage with 13B models are:
20
  | 3bpw | 8k | 15gb |
21
  | 3bpw | 4k | 12gb |
22
  I have rounded up, these arent exact numbers, this is also on a windows machine, they should be slightly lower on linux.
23
-
24
- ## Prompt template: Alpaca
25
-
26
- ```
27
- Below is an instruction that describes a task. Write a response that appropriately completes the request.
28
-
29
- ### Instruction:
30
- {prompt}
31
-
32
- ### Response:
33
-
34
- ```
 
7
 
8
  3 BPW, Head bit set to 8
9
 
10
+ ## Prompt template: Alpaca
11
+
12
+ ```
13
+ Below is an instruction that describes a task. Write a response that appropriately completes the request.
14
+
15
+ ### Instruction:
16
+ {prompt}
17
+
18
+ ### Response:
19
+
20
+ ```
21
+
22
  ## VRAM
23
  My VRAM usage with 13B models are:
24
  | Bits per weight | Context | VRAM |
 
32
  | 3bpw | 8k | 15gb |
33
  | 3bpw | 4k | 12gb |
34
  I have rounded up, these arent exact numbers, this is also on a windows machine, they should be slightly lower on linux.