bartowski commited on
Commit
4297313
1 Parent(s): 2a8351a

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: llama2
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ pipeline_tag: text-generation
7
+ tags:
8
+ - CodeMate
9
+ - Code
10
+ quantized_by: bartowski
11
+ ---
12
+
13
+ ## Exllama v2 Quantizations of CodeMate-v0.1
14
+
15
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.12">turboderp's ExLlamaV2 v0.0.12</a> for quantization.
16
+
17
+ ## The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
18
+
19
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
20
+
21
+ Conversion was done using the default calibration dataset.
22
+
23
+ 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.
24
+
25
+ Original model: https://huggingface.co/codemateai/CodeMate-v0.1
26
+
27
+
28
+ <a href="https://huggingface.co/bartowski/CodeMate-v0.1-exl2/tree/6_5">6.5 bits per weight</a>\n
29
+ <a href="https://huggingface.co/bartowski/CodeMate-v0.1-exl2/tree/4_25">4.25 bits per weight</a>\n
30
+ <a href="https://huggingface.co/bartowski/CodeMate-v0.1-exl2/tree/3_5">3.5 bits per weight</a>\n
31
+ <a href="https://huggingface.co/bartowski/CodeMate-v0.1-exl2/tree/3_0">3.0 bits per weight</a>\n
32
+ <a href="https://huggingface.co/bartowski/CodeMate-v0.1-exl2/tree/2_4">2.4 bits per weight</a>\n
33
+
34
+ ## Download instructions
35
+
36
+ With git:
37
+
38
+ ```shell
39
+ git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/CodeMate-v0.1-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 `CodeMate-v0.1-exl2`:
49
+
50
+ ```shell
51
+ mkdir CodeMate-v0.1-exl2
52
+ huggingface-cli download bartowski/CodeMate-v0.1-exl2 --local-dir CodeMate-v0.1-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 CodeMate-v0.1-exl2-6_5
61
+ huggingface-cli download bartowski/CodeMate-v0.1-exl2 --revision 6_5 --local-dir CodeMate-v0.1-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 CodeMate-v0.1-exl2-6.5
68
+ huggingface-cli download bartowski/CodeMate-v0.1-exl2 --revision 6_5 --local-dir CodeMate-v0.1-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