bartowski commited on
Commit
994d8de
1 Parent(s): 55a39c0

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +65 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ quantized_by: bartowski
5
+ pipeline_tag: text-generation
6
+ ---
7
+
8
+ ## Exllama v2 Quantizations of Gemmalpaca-7B
9
+
10
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.14">turboderp's ExLlamaV2 v0.0.14</a> for quantization.
11
+
12
+ <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
13
+
14
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
15
+
16
+ Original model: https://huggingface.co/mlabonne/Gemmalpaca-7B/
17
+
18
+ No GQA - VRAM requirements will be higher
19
+
20
+ | Branch | Bits | lm_head bits | Size (4k) | Size (16k) | Description |
21
+ | -------------------------------------------------------------- | ---- | ------------ | --------- | ---------- | ----------- |
22
+ | [8_0](https://huggingface.co/bartowski/Gemmalpaca-7B-exl2/tree/8_0) | 8.0 | 8.0 | 9.4 GB | 15.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
23
+ | [6_5](https://huggingface.co/bartowski/Gemmalpaca-7B-exl2/tree/6_5) | 6.5 | 8.0 | 8.6 GB | 14.8 GB | Near unquantized performance at vastly reduced size, **recommended**. |
24
+ | [5_0](https://huggingface.co/bartowski/Gemmalpaca-7B-exl2/tree/5_0) | 5.0 | 6.0 | 7.2 GB | 13.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards with 4k context. |
25
+ | [4_25](https://huggingface.co/bartowski/Gemmalpaca-7B-exl2/tree/4_25) | 4.25 | 6.0 | 6.5 GB | 12.7 GB | GPTQ equivalent bits per weight. |
26
+ | [3_5](https://huggingface.co/bartowski/Gemmalpaca-7B-exl2/tree/3_5) | 3.5 | 6.0 | 5.9 GB | 12.1 GB | Lower quality, not recommended. |
27
+
28
+ ## Download instructions
29
+
30
+ With git:
31
+
32
+ ```shell
33
+ git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Gemmalpaca-7B-exl2 Gemmalpaca-7B-exl2-6_5
34
+ ```
35
+
36
+ With huggingface hub (credit to TheBloke for instructions):
37
+
38
+ ```shell
39
+ pip3 install huggingface-hub
40
+ ```
41
+
42
+ To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Gemmalpaca-7B-exl2`:
43
+
44
+ ```shell
45
+ mkdir Gemmalpaca-7B-exl2
46
+ huggingface-cli download bartowski/Gemmalpaca-7B-exl2 --local-dir Gemmalpaca-7B-exl2 --local-dir-use-symlinks False
47
+ ```
48
+
49
+ To download from a different branch, add the `--revision` parameter:
50
+
51
+ Linux:
52
+
53
+ ```shell
54
+ mkdir Gemmalpaca-7B-exl2-6_5
55
+ huggingface-cli download bartowski/Gemmalpaca-7B-exl2 --revision 6_5 --local-dir Gemmalpaca-7B-exl2-6_5 --local-dir-use-symlinks False
56
+ ```
57
+
58
+ Windows (which apparently doesn't like _ in folders sometimes?):
59
+
60
+ ```shell
61
+ mkdir Gemmalpaca-7B-exl2-6.5
62
+ huggingface-cli download bartowski/Gemmalpaca-7B-exl2 --revision 6_5 --local-dir Gemmalpaca-7B-exl2-6.5 --local-dir-use-symlinks False
63
+ ```
64
+
65
+ 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