IHaveNoClueAndIMustPost commited on
Commit
b8d6a13
1 Parent(s): 3d513f8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -8,7 +8,15 @@ tags:
8
 
9
  ---
10
  A zero training self-merge test of [Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R](https://huggingface.co/Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R) using settings mentioned on [mistral-11b-slimorca](https://huggingface.co/chargoddard/mistral-11b-slimorca)<br>
 
11
 
 
 
 
 
 
 
 
12
 
13
  <b><u>Tools used / version</u></b><br>
14
  <b>Mergekit:</b> <i>c93c9bb</i><br>
 
8
 
9
  ---
10
  A zero training self-merge test of [Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R](https://huggingface.co/Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R) using settings mentioned on [mistral-11b-slimorca](https://huggingface.co/chargoddard/mistral-11b-slimorca)<br>
11
+ It's....not dumber I guess 🤷‍♀️
12
 
13
+ Simple PPL comparison<br>
14
+ <code>
15
+ <i>perplexity.exe -[MODEL] -f wiki.test.raw -b 512 -ngl 99</i><br>
16
+ <i>SFR-Iterative-DPO-LLaMA-3-8B-R-F16.gguf</i> - Final estimate: <b>PPL = 7.0279 +/- 0.04493</b><br>
17
+ <i>SFR-Iterative-DPO-LLaMA-3-11.5B-R-Q6_K.gguf</i> - Final estimate: <b>PPL = 7.0500 +/- 0.04516</b><br>
18
+ <i>Meta-Llama-3-8B-Instruct-Q6_K</i> - Final estimate: <b>PPL = 8.4727 +/- 0.06308</b>
19
+ </code>
20
 
21
  <b><u>Tools used / version</u></b><br>
22
  <b>Mergekit:</b> <i>c93c9bb</i><br>