bartowski commited on
Commit
16e59de
1 Parent(s): b93b854

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +63 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ quantized_by: bartowski
4
+ pipeline_tag: text-generation
5
+ ---
6
+
7
+ ## Exllama v2 Quantizations of Tess-10.7B-v1.5
8
+
9
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.12">turboderp's ExLlamaV2 v0.0.12</a> for quantization.
10
+
11
+ ## The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
12
+
13
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
14
+
15
+ Conversion was done using the default calibration dataset.
16
+
17
+ 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.
18
+
19
+ Original model: https://huggingface.co/migtissera/Tess-10.7B-v1.5
20
+
21
+
22
+ <a href="https://huggingface.co/bartowski/Tess-10.7B-v1.5-exl2/tree/8_0">8.0 bits per weight</a>
23
+ <a href="https://huggingface.co/bartowski/Tess-10.7B-v1.5-exl2/tree/6_5">6.5 bits per weight</a>
24
+ <a href="https://huggingface.co/bartowski/Tess-10.7B-v1.5-exl2/tree/5_0">5.0 bits per weight</a>
25
+ <a href="https://huggingface.co/bartowski/Tess-10.7B-v1.5-exl2/tree/4_25">4.25 bits per weight</a>
26
+ <a href="https://huggingface.co/bartowski/Tess-10.7B-v1.5-exl2/tree/3_5">3.5 bits per weight</a>
27
+
28
+ ## Download instructions
29
+
30
+ With git:
31
+
32
+ ```shell
33
+ git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Tess-10.7B-v1.5-exl2
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 `Tess-10.7B-v1.5-exl2`:
43
+
44
+ ```shell
45
+ mkdir Tess-10.7B-v1.5-exl2
46
+ huggingface-cli download bartowski/Tess-10.7B-v1.5-exl2 --local-dir Tess-10.7B-v1.5-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 Tess-10.7B-v1.5-exl2-6_5
55
+ huggingface-cli download bartowski/Tess-10.7B-v1.5-exl2 --revision 6_5 --local-dir Tess-10.7B-v1.5-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 Tess-10.7B-v1.5-exl2-6.5
62
+ huggingface-cli download bartowski/Tess-10.7B-v1.5-exl2 --revision 6_5 --local-dir Tess-10.7B-v1.5-exl2-6.5 --local-dir-use-symlinks False
63
+ ```
measurement.json ADDED
The diff for this file is too large to render. See raw diff