akumaburn commited on
Commit
d661a36
·
verified ·
1 Parent(s): c270ee2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -34,12 +34,16 @@ datasets:
34
 
35
  Some GGUF quantizations are included as well.
36
 
 
 
 
 
37
 
38
  llama-3-8b-bnb-4bit.Q8_0.gguf:
39
  - **MMLU-Test:** Final result: 40.4074 +/- 0.4156
40
  - **Arc-Easy:** Final result: 73.8596 +/- 1.8421
41
 
42
- Open_Orca_Llama-3-8B-unsloth.Q8_0.gguf:
43
  - **MMLU-Test:** Final result: 39.3818 +/- 0.4138
44
  - **Arc-Easy:** Final result: 67.3684 +/- 1.9656
45
 
 
34
 
35
  Some GGUF quantizations are included as well.
36
 
37
+ mistral-7b-openorca.Q8_0.gguf:
38
+ - **MMLU-Test:** Final result: 41.5836 +/- 0.4174
39
+ - **Arc-Easy:** Final result: 72.6316 +/- 1.8691
40
+ - **Truthful QA:** Final result: 32.0685 +/- 1.6339
41
 
42
  llama-3-8b-bnb-4bit.Q8_0.gguf:
43
  - **MMLU-Test:** Final result: 40.4074 +/- 0.4156
44
  - **Arc-Easy:** Final result: 73.8596 +/- 1.8421
45
 
46
+ **Open_Orca_Llama-3-8B-unsloth.Q8_0.gguf**:
47
  - **MMLU-Test:** Final result: 39.3818 +/- 0.4138
48
  - **Arc-Easy:** Final result: 67.3684 +/- 1.9656
49