SanjiWatsuki commited on
Commit
ddf6c45
•
1 Parent(s): 95327a4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -29,7 +29,7 @@ I picked these models because:
29
 
30
  Based on the parent models, I expect this model to be used with an 8192 context window. Please use NTK scaling alpha of 2.6 to experimentally try out 16383 context.
31
 
32
- **Let me be candid:** Despite the test scores, I do not believe this model is a GPT killer. I think it's a very sharp model, it probably punches way above its weight, but it's still a 7B model. Keep your expectations in check 😉
33
 
34
  **MT-Bench Average Turn**
35
  | model | score | size
 
29
 
30
  Based on the parent models, I expect this model to be used with an 8192 context window. Please use NTK scaling alpha of 2.6 to experimentally try out 16383 context.
31
 
32
+ **Let me be candid:** Despite the test scores, I do not believe this model is a GPT killer. I think it's a very sharp model, it probably punches way above its weight, but it's still a 7B model. Even for a 7B model, I think it's quirky and has some weird outputs. Keep your expectations in check 😉
33
 
34
  **MT-Bench Average Turn**
35
  | model | score | size