Hugging Face's logo

mradermacher
/
zephyr-orpo-141b-A35b-v0.1-i1-GGUF

Transformers
GGUF
English
trl
orpo
Generated from Trainer
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
68fd8fc
•
1 Parent(s): e92dd81

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
  weighted/imatrix quants of https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistral-community/Mixtral-8x22B-v0.1
3
+ datasets:
4
+ - argilla/distilabel-capybara-dpo-7k-binarized
5
+ exported_from: HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
6
+ language:
7
+ - en
8
+ library_name: transformers
9
+ license: apache-2.0
10
+ quantized_by: mradermacher
11
+ tags:
12
+ - trl
13
+ - orpo
14
+ - generated_from_trainer
15
+ ---
16
+ ## About
17
+
18
  <!-- ### quantize_version: 1 -->
19
  <!-- ### output_tensor_quantised: 1 -->
20
  <!-- ### convert_type: -->
21
  <!-- ### vocab_type: -->
22
  weighted/imatrix quants of https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
23
+
24
+
25
+ <!-- provided-files -->
26
+ static quants are available at https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-GGUF
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/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 38.0 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 46.8 | |
41
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q2_K.gguf.part2of2) | i1-Q2_K | 52.2 | IQ3_XXS probably better |
42
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ3_XXS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ3_XXS.gguf.part2of2) | i1-IQ3_XXS | 55.0 | lower quality |
43
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ3_XS.gguf.part2of2) | i1-IQ3_XS | 58.3 | |
44
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 61.6 | beats Q3_K* |
45
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 61.6 | IQ3_XS probably better |
46
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 64.6 | |
47
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 67.9 | IQ3_S probably better |
48
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 72.7 | IQ3_M probably better |
49
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 75.6 | |
50
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 80.0 | fast, low quality |
51
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 80.6 | optimal size/speed/quality |
52
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 85.7 | fast, recommended |
53
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 97.1 | |
54
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q5_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q5_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q5_K_M.gguf.part3of3) | i1-Q5_K_M | 100.1 | |
55
+ | [PART 1](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/zephyr-orpo-141b-A35b-v0.1-i1-GGUF/resolve/main/zephyr-orpo-141b-A35b-v0.1.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 115.6 | practically like static Q6_K |
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 -->