bartowski commited on
Commit
8cd1aae
1 Parent(s): 40a469e

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: cc-by-nc-4.0
3
+ language:
4
+ - en
5
+ base_model:
6
+ - upstage/SOLAR-10.7B-v1.0
7
+ quantized_by: bartowski
8
+ pipeline_tag: text-generation
9
+ ---
10
+
11
+ ## Exllama v2 Quantizations of Sensualize-Solar-10.7B
12
+
13
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</a> for quantization.
14
+
15
+ ## The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
16
+
17
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
18
+
19
+ Conversion was done using the default calibration dataset.
20
+
21
+ 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.
22
+
23
+ Original model: https://huggingface.co/Sao10K/Sensualize-Solar-10.7B
24
+
25
+
26
+
27
+ <a href="https://huggingface.co/bartowski/Sensualize-Solar-10.7B-exl2/tree/8_0">8.0 bits per weight</a>
28
+
29
+ <a href="https://huggingface.co/bartowski/Sensualize-Solar-10.7B-exl2/tree/6_5">6.5 bits per weight</a>
30
+
31
+ <a href="https://huggingface.co/bartowski/Sensualize-Solar-10.7B-exl2/tree/5_0">5.0 bits per weight</a>
32
+
33
+ <a href="https://huggingface.co/bartowski/Sensualize-Solar-10.7B-exl2/tree/4_0">4.0 bits per weight</a>
34
+
35
+ <a href="https://huggingface.co/bartowski/Sensualize-Solar-10.7B-exl2/tree/3_5">3.5 bits per weight</a>
36
+
37
+ ## Download instructions
38
+
39
+ With git:
40
+
41
+ ```shell
42
+ git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/Sensualize-Solar-10.7B-exl2
43
+ ```
44
+
45
+ With huggingface hub (credit to TheBloke for instructions):
46
+
47
+ ```shell
48
+ pip3 install huggingface-hub
49
+ ```
50
+
51
+ To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Sensualize-Solar-10.7B-exl2`:
52
+
53
+ ```shell
54
+ mkdir Sensualize-Solar-10.7B-exl2
55
+ huggingface-cli download bartowski/Sensualize-Solar-10.7B-exl2 --local-dir Sensualize-Solar-10.7B-exl2 --local-dir-use-symlinks False
56
+ ```
57
+
58
+ To download from a different branch, add the `--revision` parameter:
59
+
60
+ ```shell
61
+ mkdir Sensualize-Solar-10.7B-exl2
62
+ huggingface-cli download bartowski/Sensualize-Solar-10.7B-exl2 --revision 4_0 --local-dir Sensualize-Solar-10.7B-exl2 --local-dir-use-symlinks False
63
+ ```
measurement.json ADDED
The diff for this file is too large to render. See raw diff