mradermacher commited on
Commit
a4c01d1
1 Parent(s): af3ae60

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +72 -0
README.md CHANGED
@@ -1,6 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/VAGOsolutions/SauerkrautLM-Gemma-7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: VAGOsolutions/SauerkrautLM-Gemma-7b
3
+ language:
4
+ - de
5
+ - en
6
+ library_name: transformers
7
+ license: other
8
+ license_link: https://ai.google.dev/gemma/terms
9
+ license_name: gemma-terms-of-use
10
+ quantized_by: mradermacher
11
+ tags:
12
+ - sft
13
+ - dpo
14
+ - laserRMT
15
+ - laser-QLoRa
16
+ - finetune
17
+ - work in progress
18
+ - alpha
19
+ ---
20
+ ## About
21
+
22
  <!-- ### quantize_version: 2 -->
23
  <!-- ### output_tensor_quantised: 1 -->
24
  <!-- ### convert_type: hf -->
25
  <!-- ### vocab_type: -->
26
  <!-- ### tags: -->
27
  static quants of https://huggingface.co/VAGOsolutions/SauerkrautLM-Gemma-7b
28
+
29
+ <!-- provided-files -->
30
+ 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.
31
+ ## Usage
32
+
33
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
34
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
35
+ more details, including on how to concatenate multi-part files.
36
+
37
+ ## Provided Quants
38
+
39
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
40
+
41
+ | Link | Type | Size/GB | Notes |
42
+ |:-----|:-----|--------:|:------|
43
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.Q2_K.gguf) | Q2_K | 3.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.IQ3_XS.gguf) | IQ3_XS | 3.9 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.IQ3_S.gguf) | IQ3_S | 4.1 | beats Q3_K* |
46
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.Q3_K_S.gguf) | Q3_K_S | 4.1 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.IQ3_M.gguf) | IQ3_M | 4.2 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.Q3_K_L.gguf) | Q3_K_L | 4.8 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.IQ4_XS.gguf) | IQ4_XS | 4.9 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.Q5_K_S.gguf) | Q5_K_S | 6.1 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.Q5_K_M.gguf) | Q5_K_M | 6.2 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.Q6_K.gguf) | Q6_K | 7.1 | very good quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality |
57
+ | [GGUF](https://huggingface.co/mradermacher/SauerkrautLM-Gemma-7b-GGUF/resolve/main/SauerkrautLM-Gemma-7b.f16.gguf) | f16 | 17.2 | 16 bpw, overkill |
58
+
59
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
60
+ types (lower is better):
61
+
62
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
63
+
64
+ And here are Artefact2's thoughts on the matter:
65
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
66
+
67
+ ## FAQ / Model Request
68
+
69
+ See https://huggingface.co/mradermacher/model_requests for some answers to
70
+ questions you might have and/or if you want some other model quantized.
71
+
72
+ ## Thanks
73
+
74
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
75
+ me use its servers and providing upgrades to my workstation to enable
76
+ this work in my free time.
77
+
78
+ <!-- end -->