bartowski commited on
Commit
586c7aa
1 Parent(s): 71c066b

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +73 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-14B
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+ license: apache-2.0
9
+ quantized_by: bartowski
10
+ pipeline_tag: text-generation
11
+ ---
12
+
13
+ ## Exllama v2 Quantizations of SuperNova-Medius
14
+
15
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.2.3">turboderp's ExLlamaV2 v0.2.3</a> for quantization.
16
+
17
+ <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
18
+
19
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
20
+
21
+ Original model: https://huggingface.co/arcee-ai/SuperNova-Medius
22
+
23
+ ## Prompt format
24
+
25
+
26
+ ```
27
+ <|im_start|>system
28
+ {system_prompt}<|im_end|>
29
+ <|im_start|>user
30
+ {prompt}<|im_end|>
31
+ <|im_start|>assistant
32
+ ```
33
+
34
+ ## Available sizes
35
+
36
+ | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | Description |
37
+ | ----- | ---- | ------- | ------ | ------ | ------------ |
38
+ | [8_0](https://huggingface.co/bartowski/SuperNova-Medius-exl2/tree/8_0) | 8.0 | 8.0 | 17.4 GB | 20.9 GB | Max quality that ExLlamaV2 can produce, **recommended**. |
39
+ | [6_5](https://huggingface.co/bartowski/SuperNova-Medius-exl2/tree/6_5) | 6.5 | 8.0 | 14.6 GB | 17.5 GB | Near unquantized performance at vastly reduced size, **recommended**. |
40
+ | [5_0](https://huggingface.co/bartowski/SuperNova-Medius-exl2/tree/5_0) | 5.0 | 6.0 | 11.6 GB | 14.4 GB | Slightly lower quality vs 6.5. |
41
+ | [4_25](https://huggingface.co/bartowski/SuperNova-Medius-exl2/tree/4_25) | 4.25 | 6.0 | 10.1 GB | 13.0 GB | GPTQ equivalent bits per weight. |
42
+ | [3_5](https://huggingface.co/bartowski/SuperNova-Medius-exl2/tree/3_5) | 3.5 | 6.0 | 8.7 GB | 11.5 GB | Lower quality, not recommended. |
43
+ | [3_0](https://huggingface.co/bartowski/SuperNova-Medius-exl2/tree/3_0) | 3.0 | 6.0 | 7.8 GB | 10.5 GB | Low quality, not recommended. |
44
+
45
+ ## Download instructions
46
+
47
+ With git:
48
+
49
+ ```shell
50
+ git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/SuperNova-Medius-exl2 SuperNova-Medius-exl2-6_5
51
+ ```
52
+
53
+ With huggingface hub (credit to TheBloke for instructions):
54
+
55
+ ```shell
56
+ pip3 install huggingface-hub
57
+ ```
58
+
59
+ To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
60
+
61
+ Linux:
62
+
63
+ ```shell
64
+ huggingface-cli download bartowski/SuperNova-Medius-exl2 --revision 6_5 --local-dir SuperNova-Medius-exl2-6_5
65
+ ```
66
+
67
+ Windows (which apparently doesn't like _ in folders sometimes?):
68
+
69
+ ```shell
70
+ huggingface-cli download bartowski/SuperNova-Medius-exl2 --revision 6_5 --local-dir SuperNova-Medius-exl2-6.5
71
+ ```
72
+
73
+ 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