lmganon123 commited on
Commit
324a09c
·
verified ·
1 Parent(s): 21e0d6e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -2
README.md CHANGED
@@ -6,8 +6,6 @@ tags:
6
  - ik_llama.cpp
7
  ---
8
 
9
- Unfortunately there are some issues with tokenizer and I am quite sure it is because of imatrix in the bf16 repo. I tried using the model and it is coherent but I have no idea if it affects the quality. I will probably try to make an imatrix myself later on and requant it.
10
-
11
  IQ2_KS quant of DeepSeek-R1 I made for my 192GB DDR5 + 3090/4090. Done according to:
12
 
13
  #### `IQ2_KS` 183.004 GiB (2.339 BPW)
 
6
  - ik_llama.cpp
7
  ---
8
 
 
 
9
  IQ2_KS quant of DeepSeek-R1 I made for my 192GB DDR5 + 3090/4090. Done according to:
10
 
11
  #### `IQ2_KS` 183.004 GiB (2.339 BPW)