maddes8cht
commited on
Commit
•
4a59f63
1
Parent(s):
ad566f5
"Update README.md"
Browse files
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)
|