bartowski commited on
Commit
01e71e2
1 Parent(s): c44152e

Main branch

Browse files
Files changed (2) hide show
  1. README.md +47 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-sa-4.0
3
+ language:
4
+ - en
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - code
8
+ quantized_by: bartowski
9
+ ---
10
+
11
+ ## Exllama v2 Quantizations of sqlcoder-7b
12
+
13
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.8">turboderp's ExLlamaV2 v0.0.8</a> for quantization.
14
+
15
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
16
+
17
+ Conversion was done using Evol-Instruct-Code-80k-v1.parquet as calibration dataset.
18
+
19
+ Original model: https://huggingface.co/defog/sqlcoder-7b
20
+
21
+ ## Download instructions
22
+
23
+ With git:
24
+
25
+ ```shell
26
+ git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/sqlcoder-7b-exl2
27
+ ```
28
+
29
+ With huggingface hub (credit to TheBloke for instructions):
30
+
31
+ ```shell
32
+ pip3 install huggingface-hub
33
+ ```
34
+
35
+ To download the `main` (only useful if you only care about measurement.json) branch to a folder called `sqlcoder-7b-exl2`:
36
+
37
+ ```shell
38
+ mkdir sqlcoder-7b-exl2
39
+ huggingface-cli download bartowski/sqlcoder-7b-exl2 --local-dir sqlcoder-7b-exl2 --local-dir-use-symlinks False
40
+ ```
41
+
42
+ To download from a different branch, add the `--revision` parameter:
43
+
44
+ ```shell
45
+ mkdir sqlcoder-7b-exl2
46
+ huggingface-cli download bartowski/sqlcoder-7b-exl2 --revision 4_0 --local-dir sqlcoder-7b-exl2 --local-dir-use-symlinks False
47
+ ```
measurement.json ADDED
The diff for this file is too large to render. See raw diff