mradermacher commited on
Commit
3d95448
·
verified ·
1 Parent(s): 9860655

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +78 -0
README.md CHANGED
@@ -1,6 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: nicoboss -->
6
  weighted/imatrix quants of https://huggingface.co/Delta-Vector/Hamanasu-Magnum-QwQ-32B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Delta-Vector/Hamanasu-Magnum-QwQ-32B
3
+ datasets:
4
+ - NewEden/Orion-LIT
5
+ - NewEden/Orion-Asstr-Stories-16K
6
+ - Mielikki/Erebus-87k
7
+ - NewEden/RP-logs-V2-Experimental-prefixed
8
+ - NewEden/Creative_Writing-Complexity
9
+ - NewEden/Discord-Filtered
10
+ - NewEden/DeepseekRP-Filtered
11
+ - NewEden/Storium-Prefixed-Clean
12
+ - NewEden/Basket-Weaving-Filtered
13
+ - NewEden/LIMARP-Complexity
14
+ - NewEden/Misc-Data-Sharegpt-Prefixed
15
+ - NewEden/BlueSky-10K-Complexity
16
+ - NewEden/OpenCAI-ShareGPT
17
+ - NewEden/Basket-Weaving-Filtered
18
+ - PocketDoc/Dans-Personamaxx-VN
19
+ - PocketDoc/Dans-Kinomaxx-VanillaBackrooms
20
+ - PocketDoc/Dans-Personamaxx-Logs
21
+ - anthracite-org/kalo-opus-instruct-22k-no-refusal
22
+ - lodrick-the-lafted/kalo-opus-instruct-3k-filtered
23
+ - anthracite-org/nopm_claude_writing_fixed
24
+ - anthracite-org/kalo_opus_misc_240827
25
+ - anthracite-org/kalo_misc_part2
26
+ - NewEden/Claude-Instruct-5K
27
+ - NewEden/Claude-Instruct-2.7K
28
+ language:
29
+ - en
30
+ library_name: transformers
31
+ quantized_by: mradermacher
32
+ tags:
33
+ - qwen
34
+ - roleplay
35
+ - finetune
36
+ - storywriting
37
+ ---
38
+ ## About
39
+
40
  <!-- ### quantize_version: 2 -->
41
  <!-- ### output_tensor_quantised: 1 -->
42
  <!-- ### convert_type: hf -->
43
  <!-- ### vocab_type: -->
44
  <!-- ### tags: nicoboss -->
45
  weighted/imatrix quants of https://huggingface.co/Delta-Vector/Hamanasu-Magnum-QwQ-32B
46
+
47
+ <!-- provided-files -->
48
+ static quants are available at https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-GGUF
49
+ ## Usage
50
+
51
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
52
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
53
+ more details, including on how to concatenate multi-part files.
54
+
55
+ ## Provided Quants
56
+
57
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
58
+
59
+ | Link | Type | Size/GB | Notes |
60
+ |:-----|:-----|--------:|:------|
61
+ | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
62
+ | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF/resolve/main/Hamanasu-Magnum-QwQ-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
64
+
65
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
66
+ types (lower is better):
67
+
68
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
69
+
70
+ And here are Artefact2's thoughts on the matter:
71
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
72
+
73
+ ## FAQ / Model Request
74
+
75
+ See https://huggingface.co/mradermacher/model_requests for some answers to
76
+ questions you might have and/or if you want some other model quantized.
77
+
78
+ ## Thanks
79
+
80
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
81
+ me use its servers and providing upgrades to my workstation to enable
82
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
83
+
84
+ <!-- end -->