mradermacher commited on
Commit
46deb78
1 Parent(s): 1848c68

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +67 -0
README.md CHANGED
@@ -1,5 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 1 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  static quants of https://huggingface.co/Alsebay/NarumashiRTS-7B-V2-1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
3
+ exported_from: Alsebay/NarumashiRTS-7B-V2-1
4
+ language:
5
+ - en
6
+ library_name: transformers
7
+ license: cc-by-nc-4.0
8
+ quantized_by: mradermacher
9
+ tags:
10
+ - text-generation-inference
11
+ - transformers
12
+ - unsloth
13
+ - mistral
14
+ - trl
15
+ - sft
16
+ - Roleplay
17
+ - roleplay
18
+ ---
19
+ ## About
20
+
21
  <!-- ### quantize_version: 1 -->
22
  <!-- ### output_tensor_quantised: 1 -->
23
  <!-- ### convert_type: -->
24
  <!-- ### vocab_type: -->
25
  static quants of https://huggingface.co/Alsebay/NarumashiRTS-7B-V2-1
26
+
27
+
28
+ <!-- provided-files -->
29
+ weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
30
+ ## Usage
31
+
32
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
33
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
34
+ more details, including on how to concatenate multi-part files.
35
+
36
+ ## Provided Quants
37
+
38
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
39
+
40
+ | Link | Type | Size/GB | Notes |
41
+ |:-----|:-----|--------:|:------|
42
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.Q2_K.gguf) | Q2_K | 2.8 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
46
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.IQ3_M.gguf) | IQ3_M | 3.4 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/NarumashiRTS-7B-V2-1-GGUF/resolve/main/NarumashiRTS-7B-V2-1.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
56
+
57
+
58
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
59
+ types (lower is better):
60
+
61
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
62
+
63
+ And here are Artefact2's thoughts on the matter:
64
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
65
+
66
+ ## Thanks
67
+
68
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
69
+ me use its servers and providing upgrades to my workstation to enable
70
+ this work in my free time.
71
+
72
+ <!-- end -->