InferenceIllusionist commited on
Commit
55b4921
1 Parent(s): 5ae74ce

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -9,11 +9,13 @@ license: cc-by-nc-4.0
9
  * Model creator: [Sao10K](https://huggingface.co/Sao10K/)
10
  * Original model: [Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)
11
 
12
- <b>Important: </b> Inferencing for newer formats (IQ3_S, IQ4_NL, etc) was tested on llama.cpp. These newer quants may not work with other methods yet (as of 2/25/24).
13
 
14
 
15
  All credits to Sao10K for the original model. This is just a quick test of the new quantization types such as IQ_3S in an attempt to further reduce VRAM requirements.
16
 
 
 
17
  Quantized from fp16 with love. Importance matrix file [Fimbulvetr-11B-v2-imatrix.dat](https://huggingface.co/InferenceIllusionist/Fimbulvetr-11B-v2-iMat-GGUF/blob/main/Fimbulvetr-11B-v2-imatrix.dat) was calculated using Q8_0.
18
 
19
 
 
9
  * Model creator: [Sao10K](https://huggingface.co/Sao10K/)
10
  * Original model: [Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)
11
 
12
+ <b>Important: </b> Inferencing for newer formats i.e. IQ1_S, IQ3_S, IQ4_NL tested on latest llama.cpp & koboldcpp v.1.59.1
13
 
14
 
15
  All credits to Sao10K for the original model. This is just a quick test of the new quantization types such as IQ_3S in an attempt to further reduce VRAM requirements.
16
 
17
+
18
+
19
  Quantized from fp16 with love. Importance matrix file [Fimbulvetr-11B-v2-imatrix.dat](https://huggingface.co/InferenceIllusionist/Fimbulvetr-11B-v2-iMat-GGUF/blob/main/Fimbulvetr-11B-v2-imatrix.dat) was calculated using Q8_0.
20
 
21