measurement.json
Browse files- README.md +72 -0
- measurement.json +0 -0
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: text-generation
|
3 |
+
tags:
|
4 |
+
- merlinite
|
5 |
+
- mistral
|
6 |
+
- ibm
|
7 |
+
- lab
|
8 |
+
- labrador
|
9 |
+
- labradorite
|
10 |
+
license: apache-2.0
|
11 |
+
language:
|
12 |
+
- en
|
13 |
+
base_model: mistralai/Mistral-7B-v0.1
|
14 |
+
quantized_by: bartowski
|
15 |
+
---
|
16 |
+
|
17 |
+
## Exllama v2 Quantizations of merlinite-7b
|
18 |
+
|
19 |
+
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.14">turboderp's ExLlamaV2 v0.0.14</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 |
+
Original model: https://huggingface.co/ibm/merlinite-7b
|
26 |
+
|
27 |
+
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|
28 |
+
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
|
29 |
+
| [8_0](https://huggingface.co/bartowski/merlinite-7b-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
|
30 |
+
| [6_5](https://huggingface.co/bartowski/merlinite-7b-exl2/tree/6_5) | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
|
31 |
+
| [5_0](https://huggingface.co/bartowski/merlinite-7b-exl2/tree/5_0) | 5.0 | 6.0 | 6.0 GB | 7.4 GB | 9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
|
32 |
+
| [4_25](https://huggingface.co/bartowski/merlinite-7b-exl2/tree/4_25) | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
|
33 |
+
| [3_5](https://huggingface.co/bartowski/merlinite-7b-exl2/tree/3_5) | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |
|
34 |
+
|
35 |
+
## Download instructions
|
36 |
+
|
37 |
+
With git:
|
38 |
+
|
39 |
+
```shell
|
40 |
+
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/merlinite-7b-exl2 merlinite-7b-exl2-6_5
|
41 |
+
```
|
42 |
+
|
43 |
+
With huggingface hub (credit to TheBloke for instructions):
|
44 |
+
|
45 |
+
```shell
|
46 |
+
pip3 install huggingface-hub
|
47 |
+
```
|
48 |
+
|
49 |
+
To download the `main` (only useful if you only care about measurement.json) branch to a folder called `merlinite-7b-exl2`:
|
50 |
+
|
51 |
+
```shell
|
52 |
+
mkdir merlinite-7b-exl2
|
53 |
+
huggingface-cli download bartowski/merlinite-7b-exl2 --local-dir merlinite-7b-exl2 --local-dir-use-symlinks False
|
54 |
+
```
|
55 |
+
|
56 |
+
To download from a different branch, add the `--revision` parameter:
|
57 |
+
|
58 |
+
Linux:
|
59 |
+
|
60 |
+
```shell
|
61 |
+
mkdir merlinite-7b-exl2-6_5
|
62 |
+
huggingface-cli download bartowski/merlinite-7b-exl2 --revision 6_5 --local-dir merlinite-7b-exl2-6_5 --local-dir-use-symlinks False
|
63 |
+
```
|
64 |
+
|
65 |
+
Windows (which apparently doesn't like _ in folders sometimes?):
|
66 |
+
|
67 |
+
```shell
|
68 |
+
mkdir merlinite-7b-exl2-6.5
|
69 |
+
huggingface-cli download bartowski/merlinite-7b-exl2 --revision 6_5 --local-dir merlinite-7b-exl2-6.5 --local-dir-use-symlinks False
|
70 |
+
```
|
71 |
+
|
72 |
+
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
measurement.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|