bartowski commited on
Commit
7eb3f18
1 Parent(s): c645d46

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +62 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ tags:
4
+ - merge
5
+ - moe
6
+ quantized_by: bartowski
7
+ pipeline_tag: text-generation
8
+ ---
9
+
10
+ ## Exllama v2 Quantizations of Everyone-Coder-4x7b-Base
11
+
12
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</a> for quantization.
13
+
14
+ # The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
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 the default 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/rombodawg/Everyone-Coder-4x7b-Base
23
+
24
+
25
+
26
+ <a href="https://huggingface.co/bartowski/Everyone-Coder-4x7b-Base-exl2/tree/6_5">6.5 bits per weight</a>
27
+
28
+ <a href="https://huggingface.co/bartowski/Everyone-Coder-4x7b-Base-exl2/tree/4_25">4.25 bits per weight</a>
29
+
30
+ <a href="https://huggingface.co/bartowski/Everyone-Coder-4x7b-Base-exl2/tree/3_5">3.5 bits per weight</a>
31
+
32
+ <a href="https://huggingface.co/bartowski/Everyone-Coder-4x7b-Base-exl2/tree/3_0">3.0 bits per weight</a>
33
+
34
+ <a href="https://huggingface.co/bartowski/Everyone-Coder-4x7b-Base-exl2/tree/2_4">2.4 bits per weight</a>
35
+
36
+ ## Download instructions
37
+
38
+ With git:
39
+
40
+ ```shell
41
+ git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/Everyone-Coder-4x7b-Base-exl2
42
+ ```
43
+
44
+ With huggingface hub (credit to TheBloke for instructions):
45
+
46
+ ```shell
47
+ pip3 install huggingface-hub
48
+ ```
49
+
50
+ To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Everyone-Coder-4x7b-Base-exl2`:
51
+
52
+ ```shell
53
+ mkdir Everyone-Coder-4x7b-Base-exl2
54
+ huggingface-cli download bartowski/Everyone-Coder-4x7b-Base-exl2 --local-dir Everyone-Coder-4x7b-Base-exl2 --local-dir-use-symlinks False
55
+ ```
56
+
57
+ To download from a different branch, add the `--revision` parameter:
58
+
59
+ ```shell
60
+ mkdir Everyone-Coder-4x7b-Base-exl2
61
+ huggingface-cli download bartowski/Everyone-Coder-4x7b-Base-exl2 --revision 4_0 --local-dir Everyone-Coder-4x7b-Base-exl2 --local-dir-use-symlinks False
62
+ ```
measurement.json ADDED
The diff for this file is too large to render. See raw diff