bartowski commited on
Commit
4e65e37
1 Parent(s): a563e50

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +64 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ library_name: transformers
5
+ pipeline_tag: text-generation
6
+ datasets:
7
+ - yahma/alpaca-cleaned
8
+ license: apache-2.0
9
+ quantized_by: bartowski
10
+ ---
11
+
12
+ ## Exllama v2 Quantizations of speechless-mistral-moloras-7b
13
+
14
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</a> for quantization.
15
+
16
+ # The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
17
+
18
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
19
+
20
+ Conversion was done using the default calibration dataset.
21
+
22
+ 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.
23
+
24
+ Original model: https://huggingface.co/uukuguy/speechless-mistral-moloras-7b
25
+
26
+
27
+
28
+ <a href="https://huggingface.co/bartowski/speechless-mistral-moloras-7b-exl2/tree/8_0">8.0 bits per weight</a>
29
+
30
+ <a href="https://huggingface.co/bartowski/speechless-mistral-moloras-7b-exl2/tree/6_5">6.5 bits per weight</a>
31
+
32
+ <a href="https://huggingface.co/bartowski/speechless-mistral-moloras-7b-exl2/tree/5_0">5.0 bits per weight</a>
33
+
34
+ <a href="https://huggingface.co/bartowski/speechless-mistral-moloras-7b-exl2/tree/4_0">4.0 bits per weight</a>
35
+
36
+ <a href="https://huggingface.co/bartowski/speechless-mistral-moloras-7b-exl2/tree/3_5">3.5 bits per weight</a>
37
+
38
+ ## Download instructions
39
+
40
+ With git:
41
+
42
+ ```shell
43
+ git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/speechless-mistral-moloras-7b-exl2
44
+ ```
45
+
46
+ With huggingface hub (credit to TheBloke for instructions):
47
+
48
+ ```shell
49
+ pip3 install huggingface-hub
50
+ ```
51
+
52
+ To download the `main` (only useful if you only care about measurement.json) branch to a folder called `speechless-mistral-moloras-7b-exl2`:
53
+
54
+ ```shell
55
+ mkdir speechless-mistral-moloras-7b-exl2
56
+ huggingface-cli download bartowski/speechless-mistral-moloras-7b-exl2 --local-dir speechless-mistral-moloras-7b-exl2 --local-dir-use-symlinks False
57
+ ```
58
+
59
+ To download from a different branch, add the `--revision` parameter:
60
+
61
+ ```shell
62
+ mkdir speechless-mistral-moloras-7b-exl2
63
+ huggingface-cli download bartowski/speechless-mistral-moloras-7b-exl2 --revision 4_0 --local-dir speechless-mistral-moloras-7b-exl2 --local-dir-use-symlinks False
64
+ ```
measurement.json ADDED
The diff for this file is too large to render. See raw diff