mradermacher commited on
Commit
0f86374
1 Parent(s): 27eef8d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +70 -0
README.md CHANGED
@@ -1 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/alvarobartt/mistral-7b-orpo-capybara-reproduction
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-v0.1
3
+ datasets:
4
+ - argilla/distilabel-capybara-dpo-7k-binarized
5
+ exported_from: alvarobartt/mistral-7b-orpo-capybara-reproduction
6
+ language:
7
+ - en
8
+ library_name: transformers
9
+ license: apache-2.0
10
+ quantized_by: mradermacher
11
+ tags:
12
+ - alignment-handbook
13
+ - trl
14
+ - orpo
15
+ - generated_from_trainer
16
+ - trl
17
+ - orpo
18
+ - generated_from_trainer
19
+ ---
20
+ ## About
21
+
22
  static quants of https://huggingface.co/alvarobartt/mistral-7b-orpo-capybara-reproduction
23
+
24
+
25
+ <!-- provided-files -->
26
+ 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.
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/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q2_K.gguf) | Q2_K | 3.0 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
43
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.IQ3_M.gguf) | IQ3_M | 3.5 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q4_0.gguf) | Q4_0 | 4.4 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
49
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
50
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
55
+
56
+
57
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
58
+ types (lower is better):
59
+
60
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
61
+
62
+ And here are Artefact2's thoughts on the matter:
63
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
64
+
65
+ ## Thanks
66
+
67
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
68
+ me use its servers and providing upgrades to my workstation to enable
69
+ this work in my free time.
70
+
71
+ <!-- end -->