Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Quantized using 200 samples of 8192 tokens from an RP-oriented [PIPPA](https://huggingface.co/datasets/royallab/PIPPA-cleaned) dataset.
|
2 |
+
|
3 |
+
Branches:
|
4 |
+
- `main` -- `measurement.json`
|
5 |
+
|
6 |
+
|
7 |
+
Requires ExllamaV2 version 0.0.12 and up.
|
8 |
+
|
9 |
+
Original model link: [crestf411/daybreak-miqu-1-70b-v1.0-hf](https://huggingface.co/crestf411/daybreak-miqu-1-70b-v1.0-hf)
|
10 |
+
|
11 |
+
Original model README below.
|
12 |
+
|
13 |
+
***
|
14 |
+
|
15 |
+
Model trained on the same dataset as [daybreak-mixtral-8x7b](https://huggingface.co/crestf411/daybreak-mixtral-8x7b-v1.0-hf) except directly on miqu-1-70b.
|
16 |
+
|
17 |
+
Static and imatrix GGUF quants (thanks to [mradermacher](https://huggingface.co/mradermacher)):
|
18 |
+
|
19 |
+
* https://huggingface.co/mradermacher/daybreak-miqu-1-70b-v1.0-hf-GGUF
|
20 |
+
* https://huggingface.co/mradermacher/daybreak-miqu-1-70b-v1.0-hf-i1-GGUF
|
21 |
+
|
22 |
+
EXL2 quants:
|
23 |
+
* https://huggingface.co/crestf411/daybreak-miqu-1-70b-4.25bpw-v1.0-exl2
|
24 |
+
|
25 |
+
EXL2 measurements (for making your own quants): https://huggingface.co/crestf411/ExllamaV2-Measurements/blob/main/measurement-daybreak-miqu-1-70b-v1.0.json
|