mradermacher commited on
Commit
2c56b90
1 Parent(s): 4a887a6

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +74 -0
README.md CHANGED
@@ -1,6 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: -->
6
  static quants of https://huggingface.co/spow12/ChatWaifu_22B_v2.0_preview
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: spow12/ChatWaifu_22B_v2.0_preview
3
+ datasets:
4
+ - roleplay4fun/aesir-v1.1
5
+ - kalomaze/Opus_Instruct_3k
6
+ - Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
7
+ - Aratako/Synthetic-Japanese-Roleplay-gpt-4o-mini-39.6k-formatted
8
+ - Aratako/Synthetic-Japanese-Roleplay-NSFW-Claude-3.5s-15.3k-formatted
9
+ - SkunkworksAI/reasoning-0.01
10
+ language:
11
+ - en
12
+ - ja
13
+ library_name: transformers
14
+ license: cc-by-nc-4.0
15
+ quantized_by: mradermacher
16
+ tags:
17
+ - nsfw
18
+ - Visual novel
19
+ - roleplay
20
+ - mergekit
21
+ - merge
22
+ ---
23
+ ## About
24
+
25
  <!-- ### quantize_version: 2 -->
26
  <!-- ### output_tensor_quantised: 1 -->
27
  <!-- ### convert_type: hf -->
28
  <!-- ### vocab_type: -->
29
  <!-- ### tags: -->
30
  static quants of https://huggingface.co/spow12/ChatWaifu_22B_v2.0_preview
31
+
32
+ <!-- provided-files -->
33
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-i1-GGUF
34
+ ## Usage
35
+
36
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
37
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
38
+ more details, including on how to concatenate multi-part files.
39
+
40
+ ## Provided Quants
41
+
42
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
43
+
44
+ | Link | Type | Size/GB | Notes |
45
+ |:-----|:-----|--------:|:------|
46
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.Q2_K.gguf) | Q2_K | 8.4 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.IQ3_XS.gguf) | IQ3_XS | 9.3 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.Q3_K_S.gguf) | Q3_K_S | 9.7 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.IQ3_S.gguf) | IQ3_S | 9.8 | beats Q3_K* |
50
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.IQ3_M.gguf) | IQ3_M | 10.2 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.Q3_K_M.gguf) | Q3_K_M | 10.9 | lower quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.Q3_K_L.gguf) | Q3_K_L | 11.8 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.IQ4_XS.gguf) | IQ4_XS | 12.1 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.Q4_K_S.gguf) | Q4_K_S | 12.8 | fast, recommended |
55
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.Q4_K_M.gguf) | Q4_K_M | 13.4 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.Q5_K_S.gguf) | Q5_K_S | 15.4 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.Q5_K_M.gguf) | Q5_K_M | 15.8 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.Q6_K.gguf) | Q6_K | 18.4 | very good quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/ChatWaifu_22B_v2.0_preview-GGUF/resolve/main/ChatWaifu_22B_v2.0_preview.Q8_0.gguf) | Q8_0 | 23.7 | fast, best quality |
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 -->