bartowski commited on
Commit
f4a3cd1
1 Parent(s): 7ea1e2b

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +66 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ tags:
7
+ - tenyx-fine-tuning
8
+ - dpo
9
+ - tenyxchat
10
+ quantized_by: bartowski
11
+ pipeline_tag: text-generation
12
+ ---
13
+
14
+ ## Exllama v2 Quantizations of TenyxChat-7B-v1
15
+
16
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</a> for quantization.
17
+
18
+ # The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
19
+
20
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
21
+
22
+ Conversion was done using the default calibration dataset.
23
+
24
+ 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.
25
+
26
+ Original model: https://huggingface.co/tenyx/TenyxChat-7B-v1
27
+
28
+
29
+
30
+ <a href="https://huggingface.co/bartowski/TenyxChat-7B-v1-exl2/tree/8_0">8.0 bits per weight</a>
31
+
32
+ <a href="https://huggingface.co/bartowski/TenyxChat-7B-v1-exl2/tree/6_5">6.5 bits per weight</a>
33
+
34
+ <a href="https://huggingface.co/bartowski/TenyxChat-7B-v1-exl2/tree/5_0">5.0 bits per weight</a>
35
+
36
+ <a href="https://huggingface.co/bartowski/TenyxChat-7B-v1-exl2/tree/4_0">4.0 bits per weight</a>
37
+
38
+ <a href="https://huggingface.co/bartowski/TenyxChat-7B-v1-exl2/tree/3_5">3.5 bits per weight</a>
39
+
40
+ ## Download instructions
41
+
42
+ With git:
43
+
44
+ ```shell
45
+ git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/TenyxChat-7B-v1-exl2
46
+ ```
47
+
48
+ With huggingface hub (credit to TheBloke for instructions):
49
+
50
+ ```shell
51
+ pip3 install huggingface-hub
52
+ ```
53
+
54
+ To download the `main` (only useful if you only care about measurement.json) branch to a folder called `TenyxChat-7B-v1-exl2`:
55
+
56
+ ```shell
57
+ mkdir TenyxChat-7B-v1-exl2
58
+ huggingface-cli download bartowski/TenyxChat-7B-v1-exl2 --local-dir TenyxChat-7B-v1-exl2 --local-dir-use-symlinks False
59
+ ```
60
+
61
+ To download from a different branch, add the `--revision` parameter:
62
+
63
+ ```shell
64
+ mkdir TenyxChat-7B-v1-exl2
65
+ huggingface-cli download bartowski/TenyxChat-7B-v1-exl2 --revision 4_0 --local-dir TenyxChat-7B-v1-exl2 --local-dir-use-symlinks False
66
+ ```
measurement.json ADDED
The diff for this file is too large to render. See raw diff