bartowski commited on
Commit
740ce6b
1 Parent(s): 915dbbf

measurement.json

Browse files
Files changed (2) hide show
  1. README.md +70 -0
  2. measurement.json +0 -0
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ datasets:
4
+ - NobodyExistsOnTheInternet/ToxicQAFinal
5
+ quantized_by: bartowski
6
+ pipeline_tag: text-generation
7
+ ---
8
+
9
+ ## Exllama v2 Quantizations of Llama-3-Alpha-Centauri-v0.1
10
+
11
+ Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.1.0">turboderp's ExLlamaV2 v0.1.0</a> for quantization.
12
+
13
+ <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
14
+
15
+ Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
16
+
17
+ Original model: https://huggingface.co/fearlessdots/Llama-3-Alpha-Centauri-v0.1
18
+
19
+ ## Prompt format
20
+
21
+ ```
22
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
23
+
24
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
25
+
26
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
27
+
28
+
29
+ ```
30
+
31
+ ## Available sizes
32
+
33
+
34
+ | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (8K) | VRAM (16k) | VRAM (32k) | Description |
35
+ | ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ |
36
+ | [8_0](https://huggingface.co/bartowski/Llama-3-Alpha-Centauri-v0.1-exl2/tree/8_0) | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
37
+ | [6_5](https://huggingface.co/bartowski/Llama-3-Alpha-Centauri-v0.1-exl2/tree/6_5) | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
38
+ | [5_0](https://huggingface.co/bartowski/Llama-3-Alpha-Centauri-v0.1-exl2/tree/5_0) | 5.0 | 6.0 | 7.7 GB | 8.1 GB | 9.1 GB | 11.2 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
39
+ | [4_25](https://huggingface.co/bartowski/Llama-3-Alpha-Centauri-v0.1-exl2/tree/4_25) | 4.25 | 6.0 | 7.0 GB | 7.4 GB | 8.4 GB | 10.5 GB | GPTQ equivalent bits per weight, slightly higher quality. |
40
+ | [3_5](https://huggingface.co/bartowski/Llama-3-Alpha-Centauri-v0.1-exl2/tree/3_5) | 3.5 | 6.0 | 6.4 GB | 6.8 GB | 7.8 GB | 9.9 GB | Lower quality, only use if you have to. |
41
+
42
+ ## Download instructions
43
+
44
+ With git:
45
+
46
+ ```shell
47
+ git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Llama-3-Alpha-Centauri-v0.1-exl2 Llama-3-Alpha-Centauri-v0.1-exl2-6_5
48
+ ```
49
+
50
+ With huggingface hub (credit to TheBloke for instructions):
51
+
52
+ ```shell
53
+ pip3 install huggingface-hub
54
+ ```
55
+
56
+ To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
57
+
58
+ Linux:
59
+
60
+ ```shell
61
+ huggingface-cli download bartowski/Llama-3-Alpha-Centauri-v0.1-exl2 --revision 6_5 --local-dir Llama-3-Alpha-Centauri-v0.1-exl2-6_5
62
+ ```
63
+
64
+ Windows (which apparently doesn't like _ in folders sometimes?):
65
+
66
+ ```shell
67
+ huggingface-cli download bartowski/Llama-3-Alpha-Centauri-v0.1-exl2 --revision 6_5 --local-dir Llama-3-Alpha-Centauri-v0.1-exl2-6.5
68
+ ```
69
+
70
+ 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