mradermacher commited on
Commit
176beb9
1 Parent(s): 1f82748

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +60 -0
README.md CHANGED
@@ -1 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/Kukedlc/Ramakrishna-7b-v2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Kukedlc/Ramakrishna-7b
4
+ - Kukedlc/NeuralSirKrishna-7b
5
+ exported_from: Kukedlc/Ramakrishna-7b-v2
6
+ language:
7
+ - en
8
+ library_name: transformers
9
+ quantized_by: mradermacher
10
+ tags:
11
+ - merge
12
+ - mergekit
13
+ - lazymergekit
14
+ - Kukedlc/Ramakrishna-7b
15
+ - Kukedlc/NeuralSirKrishna-7b
16
+ ---
17
+ ## About
18
+
19
  static quants of https://huggingface.co/Kukedlc/Ramakrishna-7b-v2
20
+
21
+
22
+ <!-- provided-files -->
23
+ 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.
24
+ ## Usage
25
+
26
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
27
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
28
+ more details, including on how to concatenate multi-part files.
29
+
30
+ ## Provided Quants
31
+
32
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
33
+
34
+ | Link | Type | Size/GB | Notes |
35
+ |:-----|:-----|--------:|:------|
36
+ | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v2-GGUF/resolve/main/Ramakrishna-7b-v2.Q2_K.gguf) | Q2_K | 3.0 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v2-GGUF/resolve/main/Ramakrishna-7b-v2.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v2-GGUF/resolve/main/Ramakrishna-7b-v2.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
39
+ | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v2-GGUF/resolve/main/Ramakrishna-7b-v2.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v2-GGUF/resolve/main/Ramakrishna-7b-v2.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v2-GGUF/resolve/main/Ramakrishna-7b-v2.Q4_0.gguf) | Q4_0 | 4.4 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v2-GGUF/resolve/main/Ramakrishna-7b-v2.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v2-GGUF/resolve/main/Ramakrishna-7b-v2.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/Ramakrishna-7b-v2-GGUF/resolve/main/Ramakrishna-7b-v2.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
45
+
46
+
47
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
48
+ types (lower is better):
49
+
50
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
51
+
52
+ And here are Artefact2's thoughts on the matter:
53
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
54
+
55
+ ## Thanks
56
+
57
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
58
+ me use its servers and providing upgrades to my workstation to enable
59
+ this work in my free time.
60
+
61
+ <!-- end -->