mradermacher commited on
Commit
7809178
1 Parent(s): 5b96bd7

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +62 -0
README.md CHANGED
@@ -1 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/arcee-ai/Customer-Support-Clown-7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: arcee-ai/Customer-Support-Clown-7b
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - merge
10
+ - mergekit
11
+ - CorticalStack/pastiche-crown-clown-7b-dare-dpo
12
+ - mistralai/Mistral-7B-v0.1+predibase/customer_support
13
+ ---
14
+ ## About
15
+
16
  static quants of https://huggingface.co/arcee-ai/Customer-Support-Clown-7b
17
+
18
+
19
+ <!-- provided-files -->
20
+ 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.
21
+ ## Usage
22
+
23
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
24
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
25
+ more details, including on how to concatenate multi-part files.
26
+
27
+ ## Provided Quants
28
+
29
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
30
+
31
+ | Link | Type | Size/GB | Notes |
32
+ |:-----|:-----|--------:|:------|
33
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.Q2_K.gguf) | Q2_K | 3.0 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
37
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.IQ3_M.gguf) | IQ3_M | 3.5 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
39
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/Customer-Support-Clown-7b-GGUF/resolve/main/Customer-Support-Clown-7b.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
47
+
48
+
49
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
50
+ types (lower is better):
51
+
52
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
53
+
54
+ And here are Artefact2's thoughts on the matter:
55
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
56
+
57
+ ## Thanks
58
+
59
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
60
+ me use its servers and providing upgrades to my workstation to enable
61
+ this work in my free time.
62
+
63
+ <!-- end -->