bartowski commited on
Commit
6534b7d
1 Parent(s): 4038996

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +67 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - Open-Orca/Mistral-7B-OpenOrca
7
+ - teknium/OpenHermes-2.5-Mistral-7B
8
+ quantized_by: bartowski
9
+ pipeline_tag: text-generation
10
+ ---
11
+
12
+ ## Exllama v2 Quantizations of Orca-Hermes-7B-slerp
13
+
14
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.12">turboderp's ExLlamaV2 v0.0.12</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
+ Original model: https://huggingface.co/cris177/Orca-Hermes-7B-slerp
21
+
22
+ | Branch | Bits | lm_head bits | Size | Description |
23
+ | ----- | ---- | ------- | ------ | ------------ |
24
+ | [8_0](https://huggingface.co/Bartowski/Orca-Hermes-7B-slerp-exl2/tree/8_0) | 8.0 | 8.0 | 9.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
25
+ | [6_5](https://huggingface.co/Bartowski/Orca-Hermes-7B-slerp-exl2/tree/6_5) | 6.5 | 8.0 | 8.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
26
+ | [5_0](https://huggingface.co/Bartowski/Orca-Hermes-7B-slerp-exl2/tree/5_0) | 5.0 | 6.0 | 7.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
27
+ | [4_25](https://huggingface.co/Bartowski/Orca-Hermes-7B-slerp-exl2/tree/4_25) | 4.25 | 6.0 | 6.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
28
+ | [3_5](https://huggingface.co/Bartowski/Orca-Hermes-7B-slerp-exl2/tree/3_5) | 3.5 | 6.0 | 6.1 GB | Lower quality, only use if you have to. |
29
+
30
+ All VRAM requirements estimated from 16k context. For 32k context add ~2 GB.
31
+
32
+ ## Download instructions
33
+
34
+ With git:
35
+
36
+ ```shell
37
+ git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Orca-Hermes-7B-slerp-exl2 Orca-Hermes-7B-slerp-exl2-6_5
38
+ ```
39
+
40
+ With huggingface hub (credit to TheBloke for instructions):
41
+
42
+ ```shell
43
+ pip3 install huggingface-hub
44
+ ```
45
+
46
+ To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Orca-Hermes-7B-slerp-exl2`:
47
+
48
+ ```shell
49
+ mkdir Orca-Hermes-7B-slerp-exl2
50
+ huggingface-cli download bartowski/Orca-Hermes-7B-slerp-exl2 --local-dir Orca-Hermes-7B-slerp-exl2 --local-dir-use-symlinks False
51
+ ```
52
+
53
+ To download from a different branch, add the `--revision` parameter:
54
+
55
+ Linux:
56
+
57
+ ```shell
58
+ mkdir Orca-Hermes-7B-slerp-exl2-6_5
59
+ huggingface-cli download bartowski/Orca-Hermes-7B-slerp-exl2 --revision 6_5 --local-dir Orca-Hermes-7B-slerp-exl2-6_5 --local-dir-use-symlinks False
60
+ ```
61
+
62
+ Windows (which apparently doesn't like _ in folders sometimes?):
63
+
64
+ ```shell
65
+ mkdir Orca-Hermes-7B-slerp-exl2-6.5
66
+ huggingface-cli download bartowski/Orca-Hermes-7B-slerp-exl2 --revision 6_5 --local-dir Orca-Hermes-7B-slerp-exl2-6.5 --local-dir-use-symlinks False
67
+ ```
measurement.json ADDED
The diff for this file is too large to render. See raw diff