mradermacher commited on
Commit
ae6b518
1 Parent(s): a794085

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +99 -0
README.md CHANGED
@@ -1,5 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  static quants of https://huggingface.co/LeroyDyer/Mixtral_AI_CyberTron_DeepMind_II
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: LeroyDyer/Mixtral_AI_CyberTron_DeepMind_II
3
+ datasets:
4
+ - gretelai/synthetic_text_to_sql
5
+ - HuggingFaceTB/cosmopedia
6
+ - teknium/OpenHermes-2.5
7
+ - Open-Orca/SlimOrca
8
+ - Open-Orca/OpenOrca
9
+ - cognitivecomputations/dolphin-coder
10
+ - databricks/databricks-dolly-15k
11
+ - yahma/alpaca-cleaned
12
+ - uonlp/CulturaX
13
+ - mwitiderrick/SwahiliPlatypus
14
+ - swahili
15
+ - Rogendo/English-Swahili-Sentence-Pairs
16
+ - ise-uiuc/Magicoder-Evol-Instruct-110K
17
+ - meta-math/MetaMathQA
18
+ - abacusai/ARC_DPO_FewShot
19
+ - abacusai/MetaMath_DPO_FewShot
20
+ - abacusai/HellaSwag_DPO_FewShot
21
+ - HaltiaAI/Her-The-Movie-Samantha-and-Theodore-Dataset
22
+ - gretelai/synthetic_text_to_sql
23
+ - HuggingFaceTB/cosmopedia
24
+ - teknium/OpenHermes-2.5
25
+ - cognitivecomputations/dolphin-coder
26
+ - databricks/databricks-dolly-15k
27
+ - yahma/alpaca-cleaned
28
+ - uonlp/CulturaX
29
+ - mwitiderrick/SwahiliPlatypus
30
+ - swahili
31
+ - Rogendo/English-Swahili-Sentence-Pairs
32
+ - ise-uiuc/Magicoder-Evol-Instruct-110K
33
+ - meta-math/MetaMathQA
34
+ language:
35
+ - en
36
+ library_name: transformers
37
+ license: apache-2.0
38
+ quantized_by: mradermacher
39
+ tags:
40
+ - text-generation-inference
41
+ - transformers
42
+ - unsloth
43
+ - mistral
44
+ - trl
45
+ - sft
46
+ ---
47
+ ## About
48
+
49
  <!-- ### quantize_version: 2 -->
50
  <!-- ### output_tensor_quantised: 1 -->
51
  <!-- ### convert_type: -->
52
  <!-- ### vocab_type: -->
53
  static quants of https://huggingface.co/LeroyDyer/Mixtral_AI_CyberTron_DeepMind_II
54
+
55
+ <!-- provided-files -->
56
+ 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.
57
+ ## Usage
58
+
59
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
60
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
61
+ more details, including on how to concatenate multi-part files.
62
+
63
+ ## Provided Quants
64
+
65
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
66
+
67
+ | Link | Type | Size/GB | Notes |
68
+ |:-----|:-----|--------:|:------|
69
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.Q2_K.gguf) | Q2_K | 2.8 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
73
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.IQ3_M.gguf) | IQ3_M | 3.4 | |
74
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
75
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
76
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
78
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
79
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
80
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
81
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
82
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
83
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_CyberTron_DeepMind_II-GGUF/resolve/main/Mixtral_AI_CyberTron_DeepMind_II.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
84
+
85
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
86
+ types (lower is better):
87
+
88
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
89
+
90
+ And here are Artefact2's thoughts on the matter:
91
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
92
+
93
+ ## FAQ / Model Request
94
+
95
+ See https://huggingface.co/mradermacher/model_requests for some answers to
96
+ questions you might have and/or if you want some other model quantized.
97
+
98
+ ## Thanks
99
+
100
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
101
+ me use its servers and providing upgrades to my workstation to enable
102
+ this work in my free time.
103
+
104
+ <!-- end -->