GGUF
English
exbert
Eval Results
Inference Endpoints
Crataco commited on
Commit
cdcebb8
1 Parent(s): 6b7642c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -27,6 +27,8 @@ distilgpt2, available in as many GGUF quantization levels as possible as of Marc
27
 
28
  Importance matrix was used with context set to 1,024, created with [Kalomaze's "groups_merged.txt"](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384).
29
 
 
 
30
  |Quantization|HellaSwag|
31
  |--------|--------|
32
  |IQ1_S |25.3% |
 
27
 
28
  Importance matrix was used with context set to 1,024, created with [Kalomaze's "groups_merged.txt"](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384).
29
 
30
+ Don't ask why I did this.
31
+
32
  |Quantization|HellaSwag|
33
  |--------|--------|
34
  |IQ1_S |25.3% |