bartowski commited on
Commit
a72cf33
1 Parent(s): 4a1860e

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +69 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ quantized_by: bartowski
5
+ pipeline_tag: text-generation
6
+ ---
7
+
8
+ ## Exllama v2 Quantizations of laser-dolphin-mixtral-2x7b-dpo
9
+
10
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.13">turboderp's ExLlamaV2 v0.0.13</a> for quantization.
11
+
12
+ ## The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
13
+
14
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
15
+
16
+ Conversion was done using the default calibration dataset.
17
+
18
+ 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.
19
+
20
+ Original model: https://huggingface.co/macadeliccc/laser-dolphin-mixtral-2x7b-dpo
21
+
22
+
23
+ <a href="https://huggingface.co/bartowski/laser-dolphin-mixtral-2x7b-dpo-exl2/tree/8_0">8.0 bits per weight</a>
24
+
25
+ <a href="https://huggingface.co/bartowski/laser-dolphin-mixtral-2x7b-dpo-exl2/tree/6_5">6.5 bits per weight</a>
26
+
27
+ <a href="https://huggingface.co/bartowski/laser-dolphin-mixtral-2x7b-dpo-exl2/tree/5_0">5.0 bits per weight</a>
28
+
29
+ <a href="https://huggingface.co/bartowski/laser-dolphin-mixtral-2x7b-dpo-exl2/tree/4_25">4.25 bits per weight</a>
30
+
31
+ <a href="https://huggingface.co/bartowski/laser-dolphin-mixtral-2x7b-dpo-exl2/tree/3_5">3.5 bits per weight</a>
32
+
33
+
34
+ ## Download instructions
35
+
36
+ With git:
37
+
38
+ ```shell
39
+ git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/laser-dolphin-mixtral-2x7b-dpo-exl2
40
+ ```
41
+
42
+ With huggingface hub (credit to TheBloke for instructions):
43
+
44
+ ```shell
45
+ pip3 install huggingface-hub
46
+ ```
47
+
48
+ To download the `main` (only useful if you only care about measurement.json) branch to a folder called `laser-dolphin-mixtral-2x7b-dpo-exl2`:
49
+
50
+ ```shell
51
+ mkdir laser-dolphin-mixtral-2x7b-dpo-exl2
52
+ huggingface-cli download bartowski/laser-dolphin-mixtral-2x7b-dpo-exl2 --local-dir laser-dolphin-mixtral-2x7b-dpo-exl2 --local-dir-use-symlinks False
53
+ ```
54
+
55
+ To download from a different branch, add the `--revision` parameter:
56
+
57
+ Linux:
58
+
59
+ ```shell
60
+ mkdir laser-dolphin-mixtral-2x7b-dpo-exl2-6_5
61
+ huggingface-cli download bartowski/laser-dolphin-mixtral-2x7b-dpo-exl2 --revision 6_5 --local-dir laser-dolphin-mixtral-2x7b-dpo-exl2-6_5 --local-dir-use-symlinks False
62
+ ```
63
+
64
+ Windows (which apparently doesn't like _ in folders sometimes?):
65
+
66
+ ```shell
67
+ mkdir laser-dolphin-mixtral-2x7b-dpo-exl2-6.5
68
+ huggingface-cli download bartowski/laser-dolphin-mixtral-2x7b-dpo-exl2 --revision 6_5 --local-dir laser-dolphin-mixtral-2x7b-dpo-exl2-6.5 --local-dir-use-symlinks False
69
+ ```
measurement.json ADDED
The diff for this file is too large to render. See raw diff