FusionCow commited on
Commit
f7d15f7
·
verified ·
1 Parent(s): 23c5a52

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -19,6 +19,8 @@ You're going to need ~70gb vram to run this model. The fp8 variant will require
19
 
20
  Note the fp8 variant is ~1.6x faster than the bf16 variant.
21
 
 
 
22
  ## Installation
23
 
24
  You need `ffmpeg`, `ffprobe`, and `unzip` available on `PATH`.
 
19
 
20
  Note the fp8 variant is ~1.6x faster than the bf16 variant.
21
 
22
+ Also this model isn't SUPER great, it's just solid. I wouldn't rely on this model solely, if you're using it to produce captions for a lora, look at the captions, or pass in tags, or something.
23
+
24
  ## Installation
25
 
26
  You need `ffmpeg`, `ffprobe`, and `unzip` available on `PATH`.