measurement.json
Browse files- README.md +78 -0
- measurement.json +0 -0
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- fr
|
6 |
+
- de
|
7 |
+
- es
|
8 |
+
- it
|
9 |
+
- pt
|
10 |
+
- ru
|
11 |
+
- zh
|
12 |
+
- ja
|
13 |
+
quantized_by: bartowski
|
14 |
+
pipeline_tag: text-generation
|
15 |
+
---
|
16 |
+
|
17 |
+
## Exllama v2 Quantizations of mini-magnum-12b-v1.1
|
18 |
+
|
19 |
+
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.1.8">turboderp's ExLlamaV2 v0.1.8</a> for quantization.
|
20 |
+
|
21 |
+
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
|
22 |
+
|
23 |
+
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
|
24 |
+
|
25 |
+
Conversion was done using the default calibration dataset.
|
26 |
+
|
27 |
+
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
|
28 |
+
|
29 |
+
Original model: https://huggingface.co/intervitens/mini-magnum-12b-v1.1
|
30 |
+
|
31 |
+
|
32 |
+
<a href="https://huggingface.co/bartowski/mini-magnum-12b-v1.1-exl2/tree/8_0">8.0 bits per weight</a>
|
33 |
+
|
34 |
+
<a href="https://huggingface.co/bartowski/mini-magnum-12b-v1.1-exl2/tree/6_5">6.5 bits per weight</a>
|
35 |
+
|
36 |
+
<a href="https://huggingface.co/bartowski/mini-magnum-12b-v1.1-exl2/tree/5_0">5.0 bits per weight</a>
|
37 |
+
|
38 |
+
<a href="https://huggingface.co/bartowski/mini-magnum-12b-v1.1-exl2/tree/4_25">4.25 bits per weight</a>
|
39 |
+
|
40 |
+
<a href="https://huggingface.co/bartowski/mini-magnum-12b-v1.1-exl2/tree/3_5">3.5 bits per weight</a>
|
41 |
+
|
42 |
+
|
43 |
+
## Download instructions
|
44 |
+
|
45 |
+
With git:
|
46 |
+
|
47 |
+
```shell
|
48 |
+
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/mini-magnum-12b-v1.1-exl2
|
49 |
+
```
|
50 |
+
|
51 |
+
With huggingface hub (credit to TheBloke for instructions):
|
52 |
+
|
53 |
+
```shell
|
54 |
+
pip3 install huggingface-hub
|
55 |
+
```
|
56 |
+
|
57 |
+
To download the `main` (only useful if you only care about measurement.json) branch to a folder called `mini-magnum-12b-v1.1-exl2`:
|
58 |
+
|
59 |
+
```shell
|
60 |
+
mkdir mini-magnum-12b-v1.1-exl2
|
61 |
+
huggingface-cli download bartowski/mini-magnum-12b-v1.1-exl2 --local-dir mini-magnum-12b-v1.1-exl2
|
62 |
+
```
|
63 |
+
|
64 |
+
To download from a different branch, add the `--revision` parameter:
|
65 |
+
|
66 |
+
Linux:
|
67 |
+
|
68 |
+
```shell
|
69 |
+
mkdir mini-magnum-12b-v1.1-exl2-6_5
|
70 |
+
huggingface-cli download bartowski/mini-magnum-12b-v1.1-exl2 --revision 6_5 --local-dir mini-magnum-12b-v1.1-exl2-6_5
|
71 |
+
```
|
72 |
+
|
73 |
+
Windows (which apparently doesn't like _ in folders sometimes?):
|
74 |
+
|
75 |
+
```shell
|
76 |
+
mkdir mini-magnum-12b-v1.1-exl2-6.5
|
77 |
+
huggingface-cli download bartowski/mini-magnum-12b-v1.1-exl2 --revision 6_5 --local-dir mini-magnum-12b-v1.1-exl2-6.5
|
78 |
+
```
|
measurement.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|