Hugging Face's logo

mradermacher
/
FATLLAMA-1.7T-Instruct-i1-GGUF

Transformers
English
mergekit
Merge
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
8cf5688
·
verified ·
1 Parent(s): 7ee22cb

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -0
README.md CHANGED
@@ -1,3 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -6,3 +18,43 @@
6
  weighted/imatrix quants of https://huggingface.co/RichardErkhov/FATLLAMA-1.7T-Instruct
7
 
8
  The imatrix was created from the IQ4_XS quant.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: RichardErkhov/FATLLAMA-1.7T-Instruct
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ quantized_by: mradermacher
7
+ tags:
8
+ - mergekit
9
+ - merge
10
+ ---
11
+ ## About
12
+
13
  <!-- ### quantize_version: 2 -->
14
  <!-- ### output_tensor_quantised: 1 -->
15
  <!-- ### convert_type: hf -->
 
18
  weighted/imatrix quants of https://huggingface.co/RichardErkhov/FATLLAMA-1.7T-Instruct
19
 
20
  The imatrix was created from the IQ4_XS quant.
21
+
22
+ <!-- provided-files -->
23
+ static quants are available at https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-GGUF
24
+ ## Usage
25
+
26
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
27
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
28
+ more details, including on how to concatenate multi-part files.
29
+
30
+ ## Provided Quants
31
+
32
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
33
+
34
+ | Link | Type | Size/GB | Notes |
35
+ |:-----|:-----|--------:|:------|
36
+ | [P1](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part01of13) [P2](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part02of13) [P3](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part03of13) [P4](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part04of13) [P5](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part05of13) [P6](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part06of13) [P7](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part07of13) [P8](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part08of13) [P9](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part09of13) [P10](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part10of13) [P11](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part11of13) [P12](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part12of13) [P13](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q2_K.gguf.part13of13) | i1-Q2_K | 622.5 | IQ3_XXS probably better |
37
+ | [P1](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part01of16) [P2](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part02of16) [P3](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part03of16) [P4](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part04of16) [P5](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part05of16) [P6](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part06of16) [P7](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part07of16) [P8](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part08of16) [P9](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part09of16) [P10](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part10of16) [P11](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part11of16) [P12](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part12of16) [P13](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part13of16) [P14](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part14of16) [P15](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part15of16) [P16](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_XXS.gguf.part16of16) | i1-IQ3_XXS | 649.8 | lower quality |
38
+ | [P1](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part01of17) [P2](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part02of17) [P3](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part03of17) [P4](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part04of17) [P5](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part05of17) [P6](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part06of17) [P7](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part07of17) [P8](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part08of17) [P9](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part09of17) [P10](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part10of17) [P11](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part11of17) [P12](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part12of17) [P13](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part13of17) [P14](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part14of17) [P15](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part15of17) [P16](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part16of17) [P17](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-IQ3_M.gguf.part17of17) | i1-IQ3_M | 758.1 | |
39
+ | [P1](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part01of20) [P2](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part02of20) [P3](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part03of20) [P4](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part04of20) [P5](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part05of20) [P6](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part06of20) [P7](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part07of20) [P8](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part08of20) [P9](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part09of20) [P10](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part10of20) [P11](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part11of20) [P12](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part12of20) [P13](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part13of20) [P14](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part14of20) [P15](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part15of20) [P16](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part16of20) [P17](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part17of20) [P18](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part18of20) [P19](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part19of20) [P20](https://huggingface.co/mradermacher/FATLLAMA-1.7T-Instruct-i1-GGUF/resolve/main/FATLLAMA-1.7T-Instruct.i1-Q4_K_S.gguf.part20of20) | i1-Q4_K_S | 961.5 | optimal size/speed/quality |
40
+
41
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
42
+ types (lower is better):
43
+
44
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
45
+
46
+ And here are Artefact2's thoughts on the matter:
47
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
48
+
49
+ ## FAQ / Model Request
50
+
51
+ See https://huggingface.co/mradermacher/model_requests for some answers to
52
+ questions you might have and/or if you want some other model quantized.
53
+
54
+ ## Thanks
55
+
56
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
57
+ me use its servers and providing upgrades to my workstation to enable
58
+ 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.
59
+
60
+ <!-- end -->