bartowski commited on
Commit
4daf00b
1 Parent(s): 1c9e9a7

Main branch

Browse files
Files changed (2) hide show
  1. README.md +50 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ language:
4
+ - en
5
+ base_model: microsoft/Orca-2-13b
6
+ datasets:
7
+ - HuggingFaceH4/no_robots
8
+ quantized_by: bartowski
9
+ pipeline_tag: text-generation
10
+ ---
11
+
12
+ ## Exllama v2 Quantizations of Orca-2-13B-no_robots
13
+
14
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.9">turboderp's ExLlamaV2 v0.0.9</a> for quantization.
15
+
16
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
17
+
18
+ Conversion was done using wikitext-103-raw-v1-test.parquet as calibration dataset.
19
+
20
+ 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.
21
+
22
+ Original model: https://huggingface.co/Locutusque/Orca-2-13B-no_robots
23
+
24
+ ## Download instructions
25
+
26
+ With git:
27
+
28
+ ```shell
29
+ git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/Orca-2-13B-no_robots-exl2
30
+ ```
31
+
32
+ With huggingface hub (credit to TheBloke for instructions):
33
+
34
+ ```shell
35
+ pip3 install huggingface-hub
36
+ ```
37
+
38
+ To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Orca-2-13B-no_robots-exl2`:
39
+
40
+ ```shell
41
+ mkdir Orca-2-13B-no_robots-exl2
42
+ huggingface-cli download bartowski/Orca-2-13B-no_robots-exl2 --local-dir Orca-2-13B-no_robots-exl2 --local-dir-use-symlinks False
43
+ ```
44
+
45
+ To download from a different branch, add the `--revision` parameter:
46
+
47
+ ```shell
48
+ mkdir Orca-2-13B-no_robots-exl2
49
+ huggingface-cli download bartowski/Orca-2-13B-no_robots-exl2 --revision 4_0 --local-dir Orca-2-13B-no_robots-exl2 --local-dir-use-symlinks False
50
+ ```
measurement.json ADDED
The diff for this file is too large to render. See raw diff