Hugging Face's logo

lmstudio-community
/
Athene-70B-GGUF

Text Generation
Transformers
GGUF
English
RLHF
Nexusflow
Athene
Chat Model
Inference Endpoints
imatrix
conversational
Model card Files Community
bartowski commited on
Commit
3972991
•
0 Parent(s):

Duplicate from bartowski/Athene-70B-GGUF

Browse files
Files changed (35) hide show
  1. .gitattributes +68 -0
  2. Athene-70B-IQ2_M.gguf +3 -0
  3. Athene-70B-IQ3_M.gguf +3 -0
  4. Athene-70B-IQ3_XS.gguf +3 -0
  5. Athene-70B-IQ4_XS.gguf +3 -0
  6. Athene-70B-Q2_K.gguf +3 -0
  7. Athene-70B-Q2_K_L.gguf +3 -0
  8. Athene-70B-Q3_K_L.gguf +3 -0
  9. Athene-70B-Q3_K_M.gguf +3 -0
  10. Athene-70B-Q3_K_S.gguf +3 -0
  11. Athene-70B-Q3_K_XL.gguf +3 -0
  12. Athene-70B-Q4_K_L.gguf +3 -0
  13. Athene-70B-Q4_K_M.gguf +3 -0
  14. Athene-70B-Q4_K_S.gguf +3 -0
  15. Athene-70B-Q5_K_L/Athene-70B-Q5_K_L-00001-of-00002.gguf +3 -0
  16. Athene-70B-Q5_K_L/Athene-70B-Q5_K_L-00002-of-00002.gguf +3 -0
  17. Athene-70B-Q5_K_M/Athene-70B-Q5_K_M-00001-of-00002.gguf +3 -0
  18. Athene-70B-Q5_K_M/Athene-70B-Q5_K_M-00002-of-00002.gguf +3 -0
  19. Athene-70B-Q5_K_S.gguf +3 -0
  20. Athene-70B-Q6_K/Athene-70B-Q6_K-00001-of-00002.gguf +3 -0
  21. Athene-70B-Q6_K/Athene-70B-Q6_K-00002-of-00002.gguf +3 -0
  22. Athene-70B-Q6_K_L/Athene-70B-Q6_K_L-00001-of-00002.gguf +3 -0
  23. Athene-70B-Q6_K_L/Athene-70B-Q6_K_L-00002-of-00002.gguf +3 -0
  24. Athene-70B-Q8_0/Athene-70B-Q8_0-00001-of-00002.gguf +3 -0
  25. Athene-70B-Q8_0/Athene-70B-Q8_0-00002-of-00002.gguf +3 -0
  26. Athene-70B-f32/Athene-70B-f32-00001-of-00008.gguf +3 -0
  27. Athene-70B-f32/Athene-70B-f32-00002-of-00008.gguf +3 -0
  28. Athene-70B-f32/Athene-70B-f32-00003-of-00008.gguf +3 -0
  29. Athene-70B-f32/Athene-70B-f32-00004-of-00008.gguf +3 -0
  30. Athene-70B-f32/Athene-70B-f32-00005-of-00008.gguf +3 -0
  31. Athene-70B-f32/Athene-70B-f32-00006-of-00008.gguf +3 -0
  32. Athene-70B-f32/Athene-70B-f32-00007-of-00008.gguf +3 -0
  33. Athene-70B-f32/Athene-70B-f32-00008-of-00008.gguf +3 -0
  34. Athene-70B.imatrix +3 -0
  35. README.md +116 -0
.gitattributes ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Athene-70B-Q8_0/Athene-70B-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Athene-70B-Q8_0/Athene-70B-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Athene-70B-Q6_K_L/Athene-70B-Q6_K_L-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Athene-70B-Q6_K_L/Athene-70B-Q6_K_L-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Athene-70B-Q6_K/Athene-70B-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Athene-70B-Q6_K/Athene-70B-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Athene-70B-Q5_K_L/Athene-70B-Q5_K_L-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Athene-70B-Q5_K_L/Athene-70B-Q5_K_L-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Athene-70B-Q5_K_M/Athene-70B-Q5_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Athene-70B-Q5_K_M/Athene-70B-Q5_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Athene-70B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Athene-70B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Athene-70B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Athene-70B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Athene-70B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Athene-70B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
52
+ Athene-70B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
53
+ Athene-70B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
54
+ Athene-70B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
55
+ Athene-70B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
56
+ Athene-70B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
57
+ Athene-70B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
58
+ Athene-70B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
59
+ Athene-70B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
60
+ Athene-70B-f32/Athene-70B-f32-00001-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
61
+ Athene-70B-f32/Athene-70B-f32-00002-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
62
+ Athene-70B-f32/Athene-70B-f32-00003-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
63
+ Athene-70B-f32/Athene-70B-f32-00004-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
64
+ Athene-70B-f32/Athene-70B-f32-00005-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
65
+ Athene-70B-f32/Athene-70B-f32-00006-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
66
+ Athene-70B-f32/Athene-70B-f32-00007-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
67
+ Athene-70B-f32/Athene-70B-f32-00008-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
68
+ Athene-70B.imatrix filter=lfs diff=lfs merge=lfs -text
Athene-70B-IQ2_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:742d72597530ce6cfc714c6872819c8246ba759527335217c17021fea86e74a9
3
+ size 24119293760
Athene-70B-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5c7cb15c505b1357d67e473ffc7afd5ee527e762337c27d5564632d4a0f356
3
+ size 31937034048
Athene-70B-IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50fac5a3d8384e70fba8ed03891333185a286d16eddd2ab500e7bb6bc48efe28
3
+ size 29307729728
Athene-70B-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c45b1991d6632c2a9c0f28f092bc16e1852dec1c8579f3059656dfd15db8b3
3
+ size 37902661440
Athene-70B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eaeb31f5cc409b84fa7390b8953412fb742eeb37e0a6b5d76521548d6a85c93
3
+ size 26375108416
Athene-70B-Q2_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:914fd6ad4f085a7f5f3992953f59d5ca9f10f89a4c67b3ac4e0d40874d12a4d6
3
+ size 27401156416
Athene-70B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aabd6a46e2b20029d8ba2403eba7d63a4c1528de838ee9161f779ed906345afd
3
+ size 37140592448
Athene-70B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff65cbfcf94b16bf74d4f05ec9c0633e96470d9f48024ecc1c3d008aa43f383
3
+ size 34267494208
Athene-70B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78b25c5764b77432d2a9cebad5ad43accab4bee08e5dccceb6e30b6cebe6cfe8
3
+ size 30912051008
Athene-70B-Q3_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bec997f27ca1e5c689bf678fc3d3ac36bf71dce749a06af0744d40361e2cdb1
3
+ size 38059931456
Athene-70B-Q4_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b0c59b85b3e93f9bfbabf6dc447d05eafdb6119639e6431a26d3dc38b7364f
3
+ size 43300190016
Athene-70B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3519ee88b2fbb0da0a51887b3e7ece7454fadfb1b3c4cdd38af330f8bf16ee
3
+ size 42520393536
Athene-70B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dd2accbe292f174ce845f350bda4d08c49b442ce940f7f202e7bd5d4899d5f6
3
+ size 40347219776
Athene-70B-Q5_K_L/Athene-70B-Q5_K_L-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0504fea5e434f3df7ca05f15b7354237ba7375d847f23ca34307c0d8612a274f
3
+ size 40004113984
Athene-70B-Q5_K_L/Athene-70B-Q5_K_L-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100356039159a1c2b5190dd7627132618740356034e9cb4724fa28e649003f1c
3
+ size 10594165184
Athene-70B-Q5_K_M/Athene-70B-Q5_K_M-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90dc0954bfdffc3dcd8aa64c51f96608bdbba091a29dc5d770cbc6af7b5fd212
3
+ size 39875467232
Athene-70B-Q5_K_M/Athene-70B-Q5_K_M-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edea9e038d26d11f7e1487ce169c4a2bf4a0045168e1cbd1831dd40e6f867073
3
+ size 10074349600
Athene-70B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b9dec8463c87cad13cc2c787a69db11c56ca9245744ab6f95d01ed59107af9
3
+ size 48657446720
Athene-70B-Q6_K/Athene-70B-Q6_K-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3da1fc25a41cf38a28ced6d645cd78e0a346e7fdee05306eb56321fb7c21f83c
3
+ size 39862698848
Athene-70B-Q6_K/Athene-70B-Q6_K-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:942335d4b1dcc2fab8852bd582a8c5f3d0008cfaca1b4851811dabf920860e5a
3
+ size 18025444544
Athene-70B-Q6_K_L/Athene-70B-Q6_K_L-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124d3525693ae4c45fe73838d3d3a3574f935602f96e1804d79e2d0ae8e5956e
3
+ size 39924482848
Athene-70B-Q6_K_L/Athene-70B-Q6_K_L-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de34115c0c5bae3a9f30504e427ac8d4e4831da1b5437f6720163e8c13372c3
3
+ size 18472580352
Athene-70B-Q8_0/Athene-70B-Q8_0-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cbcab9c8371f5322360b92853caec39ee58844acd334feb88a6769b353b4f6f
3
+ size 39808935936
Athene-70B-Q8_0/Athene-70B-Q8_0-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdf71c8a72e52b288a76dc078f2161dde6a47a808a96f8be4d3a927c5a3742f
3
+ size 35166113792
Athene-70B-f32/Athene-70B-f32-00001-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cbddc6bf1f21853f57ed7aca414242fddb7f7aa3bc9c709f90b8ad5a1fb81d5
3
+ size 39376249728
Athene-70B-f32/Athene-70B-f32-00002-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:895e0a111b59925df83cb51b35cdc01a70cbec1653d43a2366883a11974a7732
3
+ size 39863425280
Athene-70B-f32/Athene-70B-f32-00003-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a387d48d7d7d1ac30197716a01eb729fbeab27691ed4a023102f57a3b93de130
3
+ size 39796316288
Athene-70B-f32/Athene-70B-f32-00004-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff0bef269d91e64b137ea8e40169e139150134f085757dc84af4d191ebf369a
3
+ size 39192369472
Athene-70B-f32/Athene-70B-f32-00005-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a13557ea4c1abb7d1056820e0e083bc09d0f036013adb1078a11c8980ce78c
3
+ size 39527847968
Athene-70B-f32/Athene-70B-f32-00006-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdf7ab00dfe2f80ac5c38dc1722c74e87a29e169090b4b707220768dd51101e4
3
+ size 39192336640
Athene-70B-f32/Athene-70B-f32-00007-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ee371a6a0ae13332d960960d18bb04a4405db54c3aff240fa9981616a21005
3
+ size 39527880768
Athene-70B-f32/Athene-70B-f32-00008-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d036a0141468f93451875f4ceafab8681c566409bd3357065bb082e0afc5b9
3
+ size 5746262592
Athene-70B.imatrix ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a72fd34c5a4b1a26702020fc3e9cea269fb66d0ff927e2921d823e31b86e6a10
3
+ size 24922298
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Nexusflow/Athene-70B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: cc-by-nc-4.0
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - RLHF
10
+ - Nexusflow
11
+ - Athene
12
+ - Chat Model
13
+ quantized_by: bartowski
14
+ ---
15
+
16
+ ## Llamacpp imatrix Quantizations of Athene-70B
17
+
18
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3412">b3412</a> for quantization.
19
+
20
+ Original model: https://huggingface.co/Nexusflow/Athene-70B
21
+
22
+ All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
23
+
24
+ Run them in [LM Studio](https://lmstudio.ai/)
25
+
26
+ ## Prompt format
27
+
28
+ ```
29
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
30
+
31
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
32
+
33
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
34
+
35
+
36
+ ```
37
+
38
+ ## Download a file (not the whole branch) from below:
39
+
40
+ | Filename | Quant type | File Size | Split | Description |
41
+ | -------- | ---------- | --------- | ----- | ----------- |
42
+ | [Athene-70B-f32.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/tree/main/Athene-70B-f32) | f32 | 282.22GB | true | Full F32 weights. |
43
+ | [Athene-70B-Q8_0.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/tree/main/Athene-70B-Q8_0) | Q8_0 | 74.98GB | true | Extremely high quality, generally unneeded but max available quant. |
44
+ | [Athene-70B-Q6_K_L.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/tree/main/Athene-70B-Q6_K_L) | Q6_K_L | 58.40GB | true | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
45
+ | [Athene-70B-Q6_K.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/tree/main/Athene-70B-Q6_K) | Q6_K | 57.89GB | true | Very high quality, near perfect, *recommended*. |
46
+ | [Athene-70B-Q5_K_L.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/tree/main/Athene-70B-Q5_K_L) | Q5_K_L | 50.60GB | true | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
47
+ | [Athene-70B-Q5_K_M.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/tree/main/Athene-70B-Q5_K_M) | Q5_K_M | 49.95GB | true | High quality, *recommended*. |
48
+ | [Athene-70B-Q5_K_S.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-Q5_K_S.gguf) | Q5_K_S | 48.66GB | false | High quality, *recommended*. |
49
+ | [Athene-70B-Q4_K_L.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-Q4_K_L.gguf) | Q4_K_L | 43.30GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
50
+ | [Athene-70B-Q4_K_M.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-Q4_K_M.gguf) | Q4_K_M | 42.52GB | false | Good quality, default size for must use cases, *recommended*. |
51
+ | [Athene-70B-Q4_K_S.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-Q4_K_S.gguf) | Q4_K_S | 40.35GB | false | Slightly lower quality with more space savings, *recommended*. |
52
+ | [Athene-70B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-Q3_K_XL.gguf) | Q3_K_XL | 38.06GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
53
+ | [Athene-70B-IQ4_XS.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-IQ4_XS.gguf) | IQ4_XS | 37.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
54
+ | [Athene-70B-Q3_K_L.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-Q3_K_L.gguf) | Q3_K_L | 37.14GB | false | Lower quality but usable, good for low RAM availability. |
55
+ | [Athene-70B-Q3_K_M.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-Q3_K_M.gguf) | Q3_K_M | 34.27GB | false | Low quality. |
56
+ | [Athene-70B-IQ3_M.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-IQ3_M.gguf) | IQ3_M | 31.94GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
57
+ | [Athene-70B-Q3_K_S.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-Q3_K_S.gguf) | Q3_K_S | 30.91GB | false | Low quality, not recommended. |
58
+ | [Athene-70B-IQ3_XS.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-IQ3_XS.gguf) | IQ3_XS | 29.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
59
+ | [Athene-70B-Q2_K_L.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-Q2_K_L.gguf) | Q2_K_L | 27.40GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
60
+ | [Athene-70B-Q2_K.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-Q2_K.gguf) | Q2_K | 26.38GB | false | Very low quality but surprisingly usable. |
61
+ | [Athene-70B-IQ2_M.gguf](https://huggingface.co/bartowski/Athene-70B-GGUF/blob/main/Athene-70B-IQ2_M.gguf) | IQ2_M | 24.12GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
62
+
63
+ ## Credits
64
+
65
+ Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset
66
+
67
+ Thank you ZeroWw for the inspiration to experiment with embed/output
68
+
69
+ ## Downloading using huggingface-cli
70
+
71
+ First, make sure you have hugginface-cli installed:
72
+
73
+ ```
74
+ pip install -U "huggingface_hub[cli]"
75
+ ```
76
+
77
+ Then, you can target the specific file you want:
78
+
79
+ ```
80
+ huggingface-cli download bartowski/Athene-70B-GGUF --include "Athene-70B-Q4_K_M.gguf" --local-dir ./
81
+ ```
82
+
83
+ If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
84
+
85
+ ```
86
+ huggingface-cli download bartowski/Athene-70B-GGUF --include "Athene-70B-Q8_0.gguf/*" --local-dir Athene-70B-Q8_0
87
+ ```
88
+
89
+ You can either specify a new local-dir (Athene-70B-Q8_0) or download them all in place (./)
90
+
91
+ ## Which file should I choose?
92
+
93
+ A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
94
+
95
+ The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
96
+
97
+ If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
98
+
99
+ If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
100
+
101
+ Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
102
+
103
+ If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
104
+
105
+ If you want to get more into the weeds, you can check out this extremely useful feature chart:
106
+
107
+ [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
108
+
109
+ But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
110
+
111
+ These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
112
+
113
+ The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
114
+
115
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
116
+