gobean commited on
Commit
b0044d2
·
verified ·
1 Parent(s): a1b4658

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -8,7 +8,7 @@ tags:
8
  gobean: Quantized to q4_0, q5_0, and q8_0 since the x_k_m variants do something weird with Mixtrals imho. I used whatever state llama.cpp was in as of 4/18/24 - this had some Mixtral fixes.
9
 
10
 
11
- ## - Original Model Card -
12
 
13
  ## Overview
14
 
 
8
  gobean: Quantized to q4_0, q5_0, and q8_0 since the x_k_m variants do something weird with Mixtrals imho. I used whatever state llama.cpp was in as of 4/18/24 - this had some Mixtral fixes.
9
 
10
 
11
+ ## - Original Model Card - https://huggingface.co/abacusai/Smaug-Mixtral-v0.1
12
 
13
  ## Overview
14