Update README.md
Browse files
README.md
CHANGED
@@ -65,4 +65,20 @@ parameters:
|
|
65 |
normalize: false
|
66 |
int8_mask: true
|
67 |
dtype: float16
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
```
|
|
|
65 |
normalize: false
|
66 |
int8_mask: true
|
67 |
dtype: float16
|
68 |
+
```
|
69 |
+
|
70 |
+
###Hope:
|
71 |
+
I hope wonderful indivitual will make some Quantization varient of this model. as i dont know how to do so and im not much interested in doing that. I am requesting wonderful people who are interested in this, to make some Quantization. please help us if you think it can be a good model.
|
72 |
+
some user in hugging face are very dedicated on making Quantization version of models. @TheBloke is one of them who have contributed a lot in Quantization of many models. i hope that dream may come true. cheers]
|
73 |
+
|
74 |
+
###citation
|
75 |
+
this repo has been used to make the merge.
|
76 |
+
|
77 |
+
```
|
78 |
+
@article{goddard2024arcee,
|
79 |
+
title={Arcee's MergeKit: A Toolkit for Merging Large Language Models},
|
80 |
+
author={Goddard, Charles and Siriwardhana, Shamane and Ehghaghi, Malikeh and Meyers, Luke and Karpukhin, Vlad and Benedict, Brian and McQuade, Mark and Solawetz, Jacob},
|
81 |
+
journal={arXiv preprint arXiv:2403.13257},
|
82 |
+
year={2024}
|
83 |
+
}
|
84 |
```
|