bartowski commited on
Commit
0bea66f
1 Parent(s): 5cb026d

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +76 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - ajibawa-2023/General-Stories-Collection
5
+ language:
6
+ - en
7
+ tags:
8
+ - story
9
+ - art
10
+ - general audience
11
+ - knowledge
12
+ quantized_by: bartowski
13
+ pipeline_tag: text-generation
14
+ ---
15
+
16
+ ## Exllama v2 Quantizations of General-Stories-Mistral-7B
17
+
18
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
19
+
20
+ <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
21
+
22
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
23
+
24
+ Original model: https://huggingface.co/ajibawa-2023/General-Stories-Mistral-7B
25
+
26
+ ## Prompt format
27
+
28
+ ```
29
+ <|im_start|>system
30
+ {system_prompt}<|im_end|>
31
+ <|im_start|>user
32
+ {prompt}<|im_end|>
33
+ <|im_start|>assistant
34
+
35
+ ```
36
+
37
+ ## Available sizes
38
+
39
+
40
+ | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
41
+ | ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
42
+ | [8_0](https://huggingface.co/bartowski/General-Stories-Mistral-7B-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
43
+ | [6_5](https://huggingface.co/bartowski/General-Stories-Mistral-7B-exl2/tree/6_5) | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
44
+ | [5_0](https://huggingface.co/bartowski/General-Stories-Mistral-7B-exl2/tree/5_0) | 5.0 | 6.0 | 6.0 GB | 7.4 GB | 9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
45
+ | [4_25](https://huggingface.co/bartowski/General-Stories-Mistral-7B-exl2/tree/4_25) | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
46
+ | [3_5](https://huggingface.co/bartowski/General-Stories-Mistral-7B-exl2/tree/3_5) | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |
47
+
48
+ ## Download instructions
49
+
50
+ With git:
51
+
52
+ ```shell
53
+ git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/General-Stories-Mistral-7B-exl2 General-Stories-Mistral-7B-exl2-6_5
54
+ ```
55
+
56
+ With huggingface hub (credit to TheBloke for instructions):
57
+
58
+ ```shell
59
+ pip3 install huggingface-hub
60
+ ```
61
+
62
+ To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
63
+
64
+ Linux:
65
+
66
+ ```shell
67
+ huggingface-cli download bartowski/General-Stories-Mistral-7B-exl2 --revision 6_5 --local-dir General-Stories-Mistral-7B-exl2-6_5 --local-dir-use-symlinks False
68
+ ```
69
+
70
+ Windows (which apparently doesn't like _ in folders sometimes?):
71
+
72
+ ```shell
73
+ huggingface-cli download bartowski/General-Stories-Mistral-7B-exl2 --revision 6_5 --local-dir General-Stories-Mistral-7B-exl2-6.5 --local-dir-use-symlinks False
74
+ ```
75
+
76
+ 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