llama-anon commited on
Commit
b43d4e7
1 Parent(s): 3bd795d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -2
README.md CHANGED
@@ -1,12 +1,39 @@
1
  ---
2
  license: agpl-3.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
 
5
 
6
- LLaMA-13B merged with Instruct-13B weights, unlike the bare weights it does not output gibberish.
7
 
8
  Quantized to 4bit (with mmap enabled)
9
 
 
 
10
  Feel free to donate:
11
 
12
- XMR: 86Z8nLSVPx3SZ5z7iWugeK5JruAeGPUJyExD9e3wdTSxUvFMhGXNG9ucPqCm8M29y1AxP6ta56GBQ4GiEUMzeew9MfX1yct
 
1
  ---
2
  license: agpl-3.0
3
  ---
4
+ LLaMA-13B merged with Instruct-13B weights, just werks.
5
+
6
+ Prompt format:
7
+
8
+ ```
9
+
10
+ user instruction here
11
+
12
+ optional additional user input
13
+
14
+ generated output
15
+
16
+ ```
17
+
18
+ Example prompt:
19
+
20
+
21
+ ```
22
+
23
+ Does this tweet have negative or positive sentiment?
24
+
25
+ i hate my life!!!!
26
+
27
+ negative
28
+
29
+ ```
30
 
31
 
 
32
 
33
  Quantized to 4bit (with mmap enabled)
34
 
35
+
36
+
37
  Feel free to donate:
38
 
39
+ XMR: ```86Z8nLSVPx3SZ5z7iWugeK5JruAeGPUJyExD9e3wdTSxUvFMhGXNG9ucPqCm8M29y1AxP6ta56GBQ4GiEUMzeew9MfX1yct```