Hugging Face's logo

mradermacher
/
Golden-Curry-12B-i1-GGUF

Transformers
GGUF
English
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
72a0052
·
verified ·
1 Parent(s): 6654855

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md CHANGED
@@ -1,6 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/GreenerPastures/Golden-Curry-12B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: GreenerPastures/Golden-Curry-12B
3
+ datasets:
4
+ - Mielikki/Erebus-87k
5
+ - PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
6
+ - NewEden/Kalo-Opus-Instruct-22k-Refusal-Murdered
7
+ - Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
8
+ - NewEden/Gryphe-Sonnet-3.5-35k-Subset
9
+ - Nitral-AI/GU_Instruct-ShareGPT
10
+ - Nitral-AI/Medical_Instruct-ShareGPT
11
+ - AquaV/Resistance-Sharegpt
12
+ - AquaV/US-Army-Survival-Sharegpt
13
+ - Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
14
+ - Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
15
+ - ResplendentAI/bluemoon
16
+ - hardlyworking/openerotica-freedomrp-sharegpt-system
17
+ - MinervaAI/Aesir-Preview
18
+ - anthracite-core/c2_logs_32k_v1.1
19
+ - Nitral-AI/Creative_Writing-ShareGPT
20
+ - PJMixers/lodrick-the-lafted_OpusStories-Story2Prompt-ShareGPT
21
+ - NewEden/Opus-accepted-hermes-rejected-shuffled
22
+ language:
23
+ - en
24
+ library_name: transformers
25
+ license: apache-2.0
26
+ quantized_by: mradermacher
27
+ ---
28
+ ## About
29
+
30
  <!-- ### quantize_version: 2 -->
31
  <!-- ### output_tensor_quantised: 1 -->
32
  <!-- ### convert_type: hf -->
33
  <!-- ### vocab_type: -->
34
  <!-- ### tags: nicoboss -->
35
  weighted/imatrix quants of https://huggingface.co/GreenerPastures/Golden-Curry-12B
36
+
37
+ <!-- provided-files -->
38
+ static quants are available at https://huggingface.co/mradermacher/Golden-Curry-12B-GGUF
39
+ ## Usage
40
+
41
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
42
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
43
+ more details, including on how to concatenate multi-part files.
44
+
45
+ ## Provided Quants
46
+
47
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
48
+
49
+ | Link | Type | Size/GB | Notes |
50
+ |:-----|:-----|--------:|:------|
51
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate |
52
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate |
53
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |
59
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality |
60
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better |
62
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* |
63
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better |
65
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better |
66
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | |
67
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality |
68
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.2 | prefer IQ4_XS |
69
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality |
70
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended |
71
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q4_1.gguf) | i1-Q4_1 | 7.9 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | |
73
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | |
74
+ | [GGUF](https://huggingface.co/mradermacher/Golden-Curry-12B-i1-GGUF/resolve/main/Golden-Curry-12B.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | practically like static Q6_K |
75
+
76
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
77
+ types (lower is better):
78
+
79
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
80
+
81
+ And here are Artefact2's thoughts on the matter:
82
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
83
+
84
+ ## FAQ / Model Request
85
+
86
+ See https://huggingface.co/mradermacher/model_requests for some answers to
87
+ questions you might have and/or if you want some other model quantized.
88
+
89
+ ## Thanks
90
+
91
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
92
+ me use its servers and providing upgrades to my workstation to enable
93
+ 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.
94
+
95
+ <!-- end -->