Transformers
GGUF
English
Korean
Not-For-All-Audiences
Inference Endpoints
mradermacher commited on
Commit
df87f9c
1 Parent(s): a1a1e26

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md CHANGED
@@ -1,5 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  weighted/imatrix quants of https://huggingface.co/maywell/PiVoT-0.1-Evil-a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: maywell/PiVoT-0.1-Evil-a
3
+ datasets:
4
+ - maywell/ko_wikidata_QA
5
+ - kyujinpy/OpenOrca-KO
6
+ - Anthropic/hh-rlhf
7
+ language:
8
+ - en
9
+ library_name: transformers
10
+ license: cc-by-sa-4.0
11
+ quantized_by: mradermacher
12
+ tags:
13
+ - not-for-all-audiences
14
+ ---
15
+ ## About
16
+
17
  <!-- ### quantize_version: 2 -->
18
  <!-- ### output_tensor_quantised: 1 -->
19
  <!-- ### convert_type: -->
20
  <!-- ### vocab_type: -->
21
  weighted/imatrix quants of https://huggingface.co/maywell/PiVoT-0.1-Evil-a
22
+
23
+
24
+ <!-- provided-files -->
25
+ static quants are available at https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-GGUF
26
+ ## Usage
27
+
28
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
29
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
30
+ more details, including on how to concatenate multi-part files.
31
+
32
+ ## Provided Quants
33
+
34
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
35
+
36
+ | Link | Type | Size/GB | Notes |
37
+ |:-----|:-----|--------:|:------|
38
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
39
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | for the desperate |
40
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* |
49
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
51
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/PiVoT-0.1-Evil-a-i1-GGUF/resolve/main/PiVoT-0.1-Evil-a.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
59
+
60
+
61
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
62
+ types (lower is better):
63
+
64
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
65
+
66
+ And here are Artefact2's thoughts on the matter:
67
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
68
+
69
+ ## FAQ / Model Request
70
+
71
+ See https://huggingface.co/mradermacher/model_requests for some answers to
72
+ questions you might have and/or if you want some other model quantized.
73
+
74
+ ## Thanks
75
+
76
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
77
+ me use its servers and providing upgrades to my workstation to enable
78
+ this work in my free time.
79
+
80
+ <!-- end -->