maddes8cht commited on
Commit
4a59f63
1 Parent(s): ad566f5

"Update README.md"

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -11,10 +11,13 @@ These will contain increasingly more content to help find the best models for a
11
  - Model creator: [mzbac](https://huggingface.co/mzbac)
12
  - Original model: [falcon-7b-instruct-grammar](https://huggingface.co/mzbac/falcon-7b-instruct-grammar)
13
 
 
14
  ***mzbac*** provides fine-tuned model variants specialized in Grammar-Correction.
15
  This is their Falcon-Version.
16
 
17
 
 
 
18
  # About GGUF format
19
 
20
  `gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
@@ -38,6 +41,7 @@ So, if possible, use K-quants.
38
  With a Q6_K you should find it really hard to find a quality difference to the original model - ask your model two times the same question and you may encounter bigger quality differences.
39
 
40
 
 
41
  # Original Model Card:
42
  <center>
43
  [![GitHub](https://maddes8cht.github.io/assets/buttons/github-io-button.png)](https://maddes8cht.github.io)
 
11
  - Model creator: [mzbac](https://huggingface.co/mzbac)
12
  - Original model: [falcon-7b-instruct-grammar](https://huggingface.co/mzbac/falcon-7b-instruct-grammar)
13
 
14
+
15
  ***mzbac*** provides fine-tuned model variants specialized in Grammar-Correction.
16
  This is their Falcon-Version.
17
 
18
 
19
+
20
+
21
  # About GGUF format
22
 
23
  `gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
 
41
  With a Q6_K you should find it really hard to find a quality difference to the original model - ask your model two times the same question and you may encounter bigger quality differences.
42
 
43
 
44
+
45
  # Original Model Card:
46
  <center>
47
  [![GitHub](https://maddes8cht.github.io/assets/buttons/github-io-button.png)](https://maddes8cht.github.io)