Hugging Face's logo

mradermacher
/
Teuken-7B-instruct-research-v0.4-i1-GGUF

Transformers
GGUF
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
b58c7aa
·
verified ·
1 Parent(s): 3ce2b21

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md CHANGED
@@ -1,6 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/openGPT-X/Teuken-7B-instruct-research-v0.4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: openGPT-X/Teuken-7B-instruct-research-v0.4
3
+ language:
4
+ - de
5
+ - bg
6
+ - cs
7
+ - da
8
+ - el
9
+ - en
10
+ - es
11
+ - et
12
+ - fi
13
+ - fr
14
+ - ga
15
+ - hr
16
+ - hu
17
+ - it
18
+ - lt
19
+ - lv
20
+ - mt
21
+ - nl
22
+ - pl
23
+ - pt
24
+ - ro
25
+ - sl
26
+ - sv
27
+ - sk
28
+ library_name: transformers
29
+ license: other
30
+ quantized_by: mradermacher
31
+ ---
32
+ ## About
33
+
34
  <!-- ### quantize_version: 2 -->
35
  <!-- ### output_tensor_quantised: 1 -->
36
  <!-- ### convert_type: hf -->
37
  <!-- ### vocab_type: -->
38
  <!-- ### tags: nicoboss -->
39
  weighted/imatrix quants of https://huggingface.co/openGPT-X/Teuken-7B-instruct-research-v0.4
40
+
41
+ <!-- provided-files -->
42
+ static quants are available at https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-GGUF
43
+ ## Usage
44
+
45
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
46
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
47
+ more details, including on how to concatenate multi-part files.
48
+
49
+ ## Provided Quants
50
+
51
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
52
+
53
+ | Link | Type | Size/GB | Notes |
54
+ |:-----|:-----|--------:|:------|
55
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ1_S.gguf) | i1-IQ1_S | 2.8 | for the desperate |
56
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ1_M.gguf) | i1-IQ1_M | 2.9 | mostly desperate |
57
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ2_S.gguf) | i1-IQ2_S | 3.2 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ2_M.gguf) | i1-IQ2_M | 3.4 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q2_K.gguf) | i1-Q2_K | 3.5 | IQ3_XXS probably better |
62
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.6 | lower quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.8 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better |
65
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ3_S.gguf) | i1-IQ3_S | 3.9 | beats Q3_K* |
66
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | |
67
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.2 | IQ3_S probably better |
68
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
69
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.4 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.6 | fast on arm, low quality |
71
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.6 | fast on arm+i8mm, low quality |
72
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.6 | fast on arm+sve, low quality |
73
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q4_0.gguf) | i1-Q4_0 | 4.6 | fast, low quality |
74
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
75
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.1 | fast, recommended |
76
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.5 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
78
+ | [GGUF](https://huggingface.co/mradermacher/Teuken-7B-instruct-research-v0.4-i1-GGUF/resolve/main/Teuken-7B-instruct-research-v0.4.i1-Q6_K.gguf) | i1-Q6_K | 6.6 | practically like static Q6_K |
79
+
80
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
81
+ types (lower is better):
82
+
83
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
84
+
85
+ And here are Artefact2's thoughts on the matter:
86
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
87
+
88
+ ## FAQ / Model Request
89
+
90
+ See https://huggingface.co/mradermacher/model_requests for some answers to
91
+ questions you might have and/or if you want some other model quantized.
92
+
93
+ ## Thanks
94
+
95
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
96
+ me use its servers and providing upgrades to my workstation to enable
97
+ 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.
98
+
99
+ <!-- end -->