bartowski commited on
Commit
fb67315
·
verified ·
1 Parent(s): 7394787

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +72 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: elinas/chronos-33b
4
+ tags:
5
+ - roleplay
6
+ - storywriting
7
+ - llama1
8
+ - finetune
9
+ - transformers
10
+ - pytorch
11
+ quantized_by: bartowski
12
+ pipeline_tag: text-generation
13
+ ---
14
+
15
+ ## Exllama v2 Quantizations of Chronos-Divergence-33B
16
+
17
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.2.1">turboderp's ExLlamaV2 v0.2.1</a> for quantization.
18
+
19
+ <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
20
+
21
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
22
+
23
+ Conversion was done using the default calibration dataset.
24
+
25
+ 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.
26
+
27
+ Original model: https://huggingface.co/ZeusLabs/Chronos-Divergence-33B
28
+
29
+
30
+ <a href="https://huggingface.co/bartowski/Chronos-Divergence-33B-exl2/tree/5_0">5.0 bits per weight</a>
31
+
32
+ <a href="https://huggingface.co/bartowski/Chronos-Divergence-33B-exl2/tree/4_25">4.25 bits per weight</a>
33
+
34
+ <a href="https://huggingface.co/bartowski/Chronos-Divergence-33B-exl2/tree/3_5">3.5 bits per weight</a>
35
+
36
+
37
+ ## Download instructions
38
+
39
+ With git:
40
+
41
+ ```shell
42
+ git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Chronos-Divergence-33B-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 `Chronos-Divergence-33B-exl2`:
52
+
53
+ ```shell
54
+ mkdir Chronos-Divergence-33B-exl2
55
+ huggingface-cli download bartowski/Chronos-Divergence-33B-exl2 --local-dir Chronos-Divergence-33B-exl2
56
+ ```
57
+
58
+ To download from a different branch, add the `--revision` parameter:
59
+
60
+ Linux:
61
+
62
+ ```shell
63
+ mkdir Chronos-Divergence-33B-exl2-6_5
64
+ huggingface-cli download bartowski/Chronos-Divergence-33B-exl2 --revision 6_5 --local-dir Chronos-Divergence-33B-exl2-6_5
65
+ ```
66
+
67
+ Windows (which apparently doesn't like _ in folders sometimes?):
68
+
69
+ ```shell
70
+ mkdir Chronos-Divergence-33B-exl2-6.5
71
+ huggingface-cli download bartowski/Chronos-Divergence-33B-exl2 --revision 6_5 --local-dir Chronos-Divergence-33B-exl2-6.5
72
+ ```
measurement.json ADDED
The diff for this file is too large to render. See raw diff