mradermacher commited on
Commit
0f018df
1 Parent(s): ccc3492

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +71 -0
README.md CHANGED
@@ -1,5 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 1 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  weighted/imatrix quants of https://huggingface.co/Kotokin/Merged-RP-Stew-V2-51B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: Kotokin/Merged-RP-Stew-V2-51B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: other
7
+ license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
8
+ license_name: yi-34b
9
+ quantized_by: mradermacher
10
+ tags:
11
+ - merge
12
+ - roleplay
13
+ - exl2
14
+ - not-for-all-audiences
15
+ ---
16
+ ## About
17
+
18
  <!-- ### quantize_version: 1 -->
19
  <!-- ### output_tensor_quantised: 1 -->
20
  <!-- ### convert_type: -->
21
  <!-- ### vocab_type: -->
22
  weighted/imatrix quants of https://huggingface.co/Kotokin/Merged-RP-Stew-V2-51B
23
+
24
+
25
+ <!-- provided-files -->
26
+ static quants are available at https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-GGUF
27
+ ## Usage
28
+
29
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
30
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
31
+ more details, including on how to concatenate multi-part files.
32
+
33
+ ## Provided Quants
34
+
35
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
36
+
37
+ | Link | Type | Size/GB | Notes |
38
+ |:-----|:-----|--------:|:------|
39
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ1_S.gguf) | i1-IQ1_S | 11.1 | for the desperate |
40
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ1_M.gguf) | i1-IQ1_M | 12.1 | for the desperate |
41
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 13.8 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 15.3 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ2_S.gguf) | i1-IQ2_S | 16.2 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ2_M.gguf) | i1-IQ2_M | 17.5 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-Q2_K.gguf) | i1-Q2_K | 19.1 | IQ3_XXS probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 19.8 | lower quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 21.2 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 22.3 | IQ3_XS probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ3_S.gguf) | i1-IQ3_S | 22.3 | beats Q3_K* |
50
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ3_M.gguf) | i1-IQ3_M | 23.2 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 24.8 | IQ3_S probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 27.0 | IQ3_M probably better |
53
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 27.5 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-Q4_0.gguf) | i1-Q4_0 | 29.1 | fast, low quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 29.2 | optimal size/speed/quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 30.8 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 35.3 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 36.2 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Merged-RP-Stew-V2-51B-i1-GGUF/resolve/main/Merged-RP-Stew-V2-51B.i1-Q6_K.gguf) | i1-Q6_K | 42.0 | practically like static Q6_K |
60
+
61
+
62
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
63
+ types (lower is better):
64
+
65
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
66
+
67
+ And here are Artefact2's thoughts on the matter:
68
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
69
+
70
+ ## Thanks
71
+
72
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
73
+ me use its servers and providing upgrades to my workstation to enable
74
+ this work in my free time.
75
+
76
+ <!-- end -->