Hugging Face's logo

mradermacher
/
Mixtral_AI_Ultron-GGUF

Transformers
GGUF
English
text-generation-inference
unsloth
mistral
trl
code
medical
farmer
doctor
Mega-Series
Cyber-Series
Role-Play
Self-Rag
ThinkingBot
milestone
mega-series
SpydazWebAI
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
b0b562b
•
1 Parent(s): 374c5c9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md CHANGED
@@ -1,5 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 1 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  static quants of https://huggingface.co/LeroyDyer/Mixtral_AI_Ultron
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: LeroyDyer/Mixtral_AI_Ultron
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
+ exported_from: LeroyDyer/Mixtral_AI_Ultron
19
+ language:
20
+ - en
21
+ library_name: transformers
22
+ license: apache-2.0
23
+ quantized_by: mradermacher
24
+ tags:
25
+ - text-generation-inference
26
+ - transformers
27
+ - unsloth
28
+ - mistral
29
+ - trl
30
+ - code
31
+ - 'medical '
32
+ - farmer
33
+ - doctor
34
+ - Mega-Series
35
+ - Cyber-Series
36
+ - Role-Play
37
+ - Self-Rag
38
+ - ThinkingBot
39
+ - milestone
40
+ - mega-series
41
+ - SpydazWebAI
42
+ ---
43
+ ## About
44
+
45
  <!-- ### quantize_version: 1 -->
46
  <!-- ### output_tensor_quantised: 1 -->
47
  <!-- ### convert_type: -->
48
  <!-- ### vocab_type: -->
49
  static quants of https://huggingface.co/LeroyDyer/Mixtral_AI_Ultron
50
+
51
+
52
+ <!-- provided-files -->
53
+ ## Usage
54
+
55
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
56
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
57
+ more details, including on how to concatenate multi-part files.
58
+
59
+ ## Provided Quants
60
+
61
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
62
+
63
+ | Link | Type | Size/GB | Notes |
64
+ |:-----|:-----|--------:|:------|
65
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.Q2_K.gguf) | Q2_K | 2.8 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
67
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
68
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
69
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.IQ3_M.gguf) | IQ3_M | 3.4 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
71
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
73
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
74
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
75
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
76
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
78
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
79
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral_AI_Ultron-i1-GGUF/resolve/main/Mixtral_AI_Ultron.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
80
+
81
+
82
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
83
+ types (lower is better):
84
+
85
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
86
+
87
+ And here are Artefact2's thoughts on the matter:
88
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
89
+
90
+ ## Thanks
91
+
92
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
93
+ me use its servers and providing upgrades to my workstation to enable
94
+ this work in my free time.
95
+
96
+ <!-- end -->