mradermacher commited on
Commit
a88e237
1 Parent(s): 49ec792

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +118 -0
README.md CHANGED
@@ -1,6 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/FreedomIntelligence/Apollo2-9B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: FreedomIntelligence/Apollo2-9B
3
+ datasets:
4
+ - FreedomIntelligence/ApolloMoEDataset
5
+ language:
6
+ - ar
7
+ - en
8
+ - zh
9
+ - ko
10
+ - ja
11
+ - mn
12
+ - th
13
+ - vi
14
+ - lo
15
+ - mg
16
+ - de
17
+ - pt
18
+ - es
19
+ - fr
20
+ - ru
21
+ - it
22
+ - hr
23
+ - gl
24
+ - cs
25
+ - co
26
+ - la
27
+ - uk
28
+ - bs
29
+ - bg
30
+ - eo
31
+ - sq
32
+ - da
33
+ - sa
34
+ - no
35
+ - gn
36
+ - sr
37
+ - sk
38
+ - gd
39
+ - lb
40
+ - hi
41
+ - ku
42
+ - mt
43
+ - he
44
+ - ln
45
+ - bm
46
+ - sw
47
+ - ig
48
+ - rw
49
+ - ha
50
+ library_name: transformers
51
+ license: apache-2.0
52
+ quantized_by: mradermacher
53
+ tags:
54
+ - biology
55
+ - medical
56
+ ---
57
+ ## About
58
+
59
  <!-- ### quantize_version: 2 -->
60
  <!-- ### output_tensor_quantised: 1 -->
61
  <!-- ### convert_type: hf -->
62
  <!-- ### vocab_type: -->
63
  <!-- ### tags: nicoboss -->
64
  weighted/imatrix quants of https://huggingface.co/FreedomIntelligence/Apollo2-9B
65
+
66
+ <!-- provided-files -->
67
+ static quants are available at https://huggingface.co/mradermacher/Apollo2-9B-GGUF
68
+ ## Usage
69
+
70
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
71
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
72
+ more details, including on how to concatenate multi-part files.
73
+
74
+ ## Provided Quants
75
+
76
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
77
+
78
+ | Link | Type | Size/GB | Notes |
79
+ |:-----|:-----|--------:|:------|
80
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate |
81
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.6 | mostly desperate |
82
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.9 | |
83
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | |
84
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.3 | |
85
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.5 | |
86
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality |
87
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better |
88
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 | |
89
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* |
90
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better |
91
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | |
92
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better |
93
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better |
94
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | |
95
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 5.5 | fast on arm, low quality |
96
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 5.5 | fast on arm+i8mm, low quality |
97
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 5.5 | fast on arm+sve, low quality |
98
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality |
99
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality |
100
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended |
101
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | |
102
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 | |
103
+ | [GGUF](https://huggingface.co/mradermacher/Apollo2-9B-i1-GGUF/resolve/main/Apollo2-9B.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | practically like static Q6_K |
104
+
105
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
106
+ types (lower is better):
107
+
108
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
109
+
110
+ And here are Artefact2's thoughts on the matter:
111
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
112
+
113
+ ## FAQ / Model Request
114
+
115
+ See https://huggingface.co/mradermacher/model_requests for some answers to
116
+ questions you might have and/or if you want some other model quantized.
117
+
118
+ ## Thanks
119
+
120
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
121
+ me use its servers and providing upgrades to my workstation to enable
122
+ 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.
123
+
124
+ <!-- end -->