bartowski commited on
Commit
6a044cb
1 Parent(s): fa320dd

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +75 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: yi-license
4
+ license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
5
+ language:
6
+ - en
7
+ library_name: transformers
8
+ base_model: []
9
+ tags:
10
+ - mergekit
11
+ - merge
12
+ - Yi
13
+ - exllama
14
+ - exllamav2
15
+ - exl2
16
+ quantized_by: bartowski
17
+ pipeline_tag: text-generation
18
+ ---
19
+
20
+ ## Exllama v2 Quantizations of Yi-34B-200K-RPMerge
21
+
22
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.13">turboderp's ExLlamaV2 v0.0.13</a> for quantization.
23
+
24
+ <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
25
+
26
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
27
+
28
+ Original model: https://huggingface.co/brucethemoose/Yi-34B-200K-RPMerge
29
+
30
+ | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
31
+ | ------ | ---- | ------------ | ---- | ---- | ---- | ----------- |
32
+ | [6_5](https://huggingface.co/bartowski/Yi-34B-200K-RPMerge-exl2/tree/6_5) | 6.5 | 8.0 | 28.9 GB | 31.6 GB | 35.6 GB | Near unquantized performance at vastly reduced size, **recommended**. |
33
+ | [4_25](https://huggingface.co/bartowski/Yi-34B-200K-RPMerge-exl2/tree/4_25) | 4.25 | 6.0 | 19.5 GB | 22.2 GB | 26.2 GB | GPTQ equivalent bits per weight, slightly higher quality. |
34
+ | [3_5](https://huggingface.co/bartowski/Yi-34B-200K-RPMerge-exl2/tree/3_5) | 3.5 | 6.0 | 16.5 GB | 19.2 GB | 23.2 GB | Lower quality, only use if you have to. |
35
+ | [3_0](https://huggingface.co/bartowski/Yi-34B-200K-RPMerge-exl2/tree/3_0) | 3.0 | 6.0 | 14.3 GB | 17.0 GB | 21.0 GB | Very low quality, usable with 16gb of VRAM. |
36
+ | [2_4](https://huggingface.co/bartowski/Yi-34B-200K-RPMerge-exl2/tree/3_0) | 2.4 | 6.0 | 12.0 GB | 14.7 GB | 18.7 GB | Extremely low quality, only recommended if trying to fit into 12GB with under 4k context. |
37
+
38
+ ## Download instructions
39
+
40
+ With git:
41
+
42
+ ```shell
43
+ git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Yi-34B-200K-RPMerge-exl2 Yi-34B-200K-RPMerge-exl2-6_5
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 `Yi-34B-200K-RPMerge-exl2`:
53
+
54
+ ```shell
55
+ mkdir Yi-34B-200K-RPMerge-exl2
56
+ huggingface-cli download bartowski/Yi-34B-200K-RPMerge-exl2 --local-dir Yi-34B-200K-RPMerge-exl2 --local-dir-use-symlinks False
57
+ ```
58
+
59
+ To download from a different branch, add the `--revision` parameter:
60
+
61
+ Linux:
62
+
63
+ ```shell
64
+ mkdir Yi-34B-200K-RPMerge-exl2-6_5
65
+ huggingface-cli download bartowski/Yi-34B-200K-RPMerge-exl2 --revision 6_5 --local-dir Yi-34B-200K-RPMerge-exl2-6_5 --local-dir-use-symlinks False
66
+ ```
67
+
68
+ Windows (which apparently doesn't like _ in folders sometimes?):
69
+
70
+ ```shell
71
+ mkdir Yi-34B-200K-RPMerge-exl2-6.5
72
+ huggingface-cli download bartowski/Yi-34B-200K-RPMerge-exl2 --revision 6_5 --local-dir Yi-34B-200K-RPMerge-exl2-6.5 --local-dir-use-symlinks False
73
+ ```
74
+
75
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
measurement.json ADDED
The diff for this file is too large to render. See raw diff