Hugging Face's logo

lmstudio-community
/
Llama-3-Groq-70B-Tool-Use-GGUF

Text Generation
GGUF
PyTorch
English
facebook
meta
llama
llama-3
groq
tool-use
function-calling
imatrix
Model card Files Community
bartowski commited on
Commit
2728352
•
0 Parent(s):

Duplicate from bartowski/Llama-3-Groq-70B-Tool-Use-GGUF

Browse files
Files changed (35) hide show
  1. .gitattributes +68 -0
  2. Llama-3-Groq-70B-Tool-Use-IQ2_M.gguf +3 -0
  3. Llama-3-Groq-70B-Tool-Use-IQ3_M.gguf +3 -0
  4. Llama-3-Groq-70B-Tool-Use-IQ3_XS.gguf +3 -0
  5. Llama-3-Groq-70B-Tool-Use-IQ4_XS.gguf +3 -0
  6. Llama-3-Groq-70B-Tool-Use-Q2_K.gguf +3 -0
  7. Llama-3-Groq-70B-Tool-Use-Q2_K_L.gguf +3 -0
  8. Llama-3-Groq-70B-Tool-Use-Q3_K_L.gguf +3 -0
  9. Llama-3-Groq-70B-Tool-Use-Q3_K_M.gguf +3 -0
  10. Llama-3-Groq-70B-Tool-Use-Q3_K_S.gguf +3 -0
  11. Llama-3-Groq-70B-Tool-Use-Q3_K_XL.gguf +3 -0
  12. Llama-3-Groq-70B-Tool-Use-Q4_K_L.gguf +3 -0
  13. Llama-3-Groq-70B-Tool-Use-Q4_K_M.gguf +3 -0
  14. Llama-3-Groq-70B-Tool-Use-Q4_K_S.gguf +3 -0
  15. Llama-3-Groq-70B-Tool-Use-Q5_K_L/Llama-3-Groq-70B-Tool-Use-Q5_K_L-00001-of-00002.gguf +3 -0
  16. Llama-3-Groq-70B-Tool-Use-Q5_K_L/Llama-3-Groq-70B-Tool-Use-Q5_K_L-00002-of-00002.gguf +3 -0
  17. Llama-3-Groq-70B-Tool-Use-Q5_K_M/Llama-3-Groq-70B-Tool-Use-Q5_K_M-00001-of-00002.gguf +3 -0
  18. Llama-3-Groq-70B-Tool-Use-Q5_K_M/Llama-3-Groq-70B-Tool-Use-Q5_K_M-00002-of-00002.gguf +3 -0
  19. Llama-3-Groq-70B-Tool-Use-Q5_K_S.gguf +3 -0
  20. Llama-3-Groq-70B-Tool-Use-Q6_K/Llama-3-Groq-70B-Tool-Use-Q6_K-00001-of-00002.gguf +3 -0
  21. Llama-3-Groq-70B-Tool-Use-Q6_K/Llama-3-Groq-70B-Tool-Use-Q6_K-00002-of-00002.gguf +3 -0
  22. Llama-3-Groq-70B-Tool-Use-Q6_K_L/Llama-3-Groq-70B-Tool-Use-Q6_K_L-00001-of-00002.gguf +3 -0
  23. Llama-3-Groq-70B-Tool-Use-Q6_K_L/Llama-3-Groq-70B-Tool-Use-Q6_K_L-00002-of-00002.gguf +3 -0
  24. Llama-3-Groq-70B-Tool-Use-Q8_0/Llama-3-Groq-70B-Tool-Use-Q8_0-00001-of-00002.gguf +3 -0
  25. Llama-3-Groq-70B-Tool-Use-Q8_0/Llama-3-Groq-70B-Tool-Use-Q8_0-00002-of-00002.gguf +3 -0
  26. Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00001-of-00008.gguf +3 -0
  27. Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00002-of-00008.gguf +3 -0
  28. Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00003-of-00008.gguf +3 -0
  29. Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00004-of-00008.gguf +3 -0
  30. Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00005-of-00008.gguf +3 -0
  31. Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00006-of-00008.gguf +3 -0
  32. Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00007-of-00008.gguf +3 -0
  33. Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00008-of-00008.gguf +3 -0
  34. Llama-3-Groq-70B-Tool-Use.imatrix +3 -0
  35. README.md +119 -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
+ Llama-3-Groq-70B-Tool-Use-Q8_0/Llama-3-Groq-70B-Tool-Use-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Llama-3-Groq-70B-Tool-Use-Q8_0/Llama-3-Groq-70B-Tool-Use-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama-3-Groq-70B-Tool-Use-Q6_K_L/Llama-3-Groq-70B-Tool-Use-Q6_K_L-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama-3-Groq-70B-Tool-Use-Q6_K_L/Llama-3-Groq-70B-Tool-Use-Q6_K_L-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama-3-Groq-70B-Tool-Use-Q6_K/Llama-3-Groq-70B-Tool-Use-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama-3-Groq-70B-Tool-Use-Q6_K/Llama-3-Groq-70B-Tool-Use-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Llama-3-Groq-70B-Tool-Use-Q5_K_L/Llama-3-Groq-70B-Tool-Use-Q5_K_L-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Llama-3-Groq-70B-Tool-Use-Q5_K_L/Llama-3-Groq-70B-Tool-Use-Q5_K_L-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Llama-3-Groq-70B-Tool-Use-Q5_K_M/Llama-3-Groq-70B-Tool-Use-Q5_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Llama-3-Groq-70B-Tool-Use-Q5_K_M/Llama-3-Groq-70B-Tool-Use-Q5_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Llama-3-Groq-70B-Tool-Use-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Llama-3-Groq-70B-Tool-Use-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Llama-3-Groq-70B-Tool-Use-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Llama-3-Groq-70B-Tool-Use-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Llama-3-Groq-70B-Tool-Use-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Llama-3-Groq-70B-Tool-Use-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
52
+ Llama-3-Groq-70B-Tool-Use-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
53
+ Llama-3-Groq-70B-Tool-Use-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
54
+ Llama-3-Groq-70B-Tool-Use-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
55
+ Llama-3-Groq-70B-Tool-Use-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
56
+ Llama-3-Groq-70B-Tool-Use-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
57
+ Llama-3-Groq-70B-Tool-Use-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
58
+ Llama-3-Groq-70B-Tool-Use-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
59
+ Llama-3-Groq-70B-Tool-Use-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
60
+ Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00001-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
61
+ Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00002-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
62
+ Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00003-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
63
+ Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00004-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
64
+ Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00005-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
65
+ Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00006-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
66
+ Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00007-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
67
+ Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00008-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
68
+ Llama-3-Groq-70B-Tool-Use.imatrix filter=lfs diff=lfs merge=lfs -text
Llama-3-Groq-70B-Tool-Use-IQ2_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b26b523465cee4956537c66b64c56337a0233ac9e131ddf5cfa4332baa22db
3
+ size 24119348832
Llama-3-Groq-70B-Tool-Use-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295ee4ef7fff253640fcafb8713878f3793b70d056cd0b168078d7b10139c02d
3
+ size 31937095648
Llama-3-Groq-70B-Tool-Use-IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb724a728e98cfdc7faec723e7ea2cca04fd175dd356bd87230833ebdb4aa55
3
+ size 29307791328
Llama-3-Groq-70B-Tool-Use-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ea35ad1f1c5d4285ec1b33067fb1d9ee9b6b51d9f3f50f763da4854122a5ff
3
+ size 37902728032
Llama-3-Groq-70B-Tool-Use-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bba8ca7647bc656d261cca43e594b237619ddcf32c23b2c303c516011b969fc
3
+ size 26375165024
Llama-3-Groq-70B-Tool-Use-Q2_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ab2f83a098767a2ddabe56a0135b1bb77e47c579e55b96681f183f0408918b
3
+ size 27401261024
Llama-3-Groq-70B-Tool-Use-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8914d36994ef9dd0587ee8ea408747530edb9cfa9d8fa1ebf6448a38782454fb
3
+ size 37140654048
Llama-3-Groq-70B-Tool-Use-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04c56167f7426d8e49417cbc5a664b36fe27b9640069455019785c5d01483398
3
+ size 34267555808
Llama-3-Groq-70B-Tool-Use-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc73b351b2cf9315e186e422937189975c1c31fc305719e059942ca1b4d3c04
3
+ size 30912112608
Llama-3-Groq-70B-Tool-Use-Q3_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f0e752c91d45cc9720905ca80ee1439d132908388659b6105ad7f0e60a1b3d
3
+ size 38060036064
Llama-3-Groq-70B-Tool-Use-Q4_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca43e7daf3976b3f3a3857ae20e680ed8b921b47c035eb4a689d74eacfdc044
3
+ size 43300294624
Llama-3-Groq-70B-Tool-Use-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28916ec25b572a0cc3746cff7502024f357f6bcd2b3d39661cec24cf0bd8ec91
3
+ size 42520461664
Llama-3-Groq-70B-Tool-Use-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60b1f14c82e860c4014bc510210d1e6c52145fa8078a7e47c1fd78f05294b69
3
+ size 40347287904
Llama-3-Groq-70B-Tool-Use-Q5_K_L/Llama-3-Groq-70B-Tool-Use-Q5_K_L-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f826f96dbec75e6a5c023dae4124317c804e11aafb5a412c9e633ccf9382ca3e
3
+ size 40004166368
Llama-3-Groq-70B-Tool-Use-Q5_K_L/Llama-3-Groq-70B-Tool-Use-Q5_K_L-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a8541fcbe91b34eec75bdb05ee9b8e9260cc98c5374e1f9d2cbadb93d0a46b
3
+ size 10594217408
Llama-3-Groq-70B-Tool-Use-Q5_K_M/Llama-3-Groq-70B-Tool-Use-Q5_K_M-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c094f05fd773ac6c98363f77d00b0d125801dd5bab7d1757312f50ea0bcd0624
3
+ size 39875501184
Llama-3-Groq-70B-Tool-Use-Q5_K_M/Llama-3-Groq-70B-Tool-Use-Q5_K_M-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc229a52c0b40edad47d91b0a08949e6db8ee132d3f088fbac5f4e0bd21e2c0d
3
+ size 10074389920
Llama-3-Groq-70B-Tool-Use-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37978be9b542e5dcdab5688f48f66e10ff04edb57884b10dc5e9c331035a5d32
3
+ size 48657520992
Llama-3-Groq-70B-Tool-Use-Q6_K/Llama-3-Groq-70B-Tool-Use-Q6_K-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e24f0bd4ae8fb4bc5cda9998df82326526db3621ec9d9dd70f6969adc966eba
3
+ size 39862739296
Llama-3-Groq-70B-Tool-Use-Q6_K/Llama-3-Groq-70B-Tool-Use-Q6_K-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede6d2ad0e3bdadddf33b7f4715b07e688ea5351823d8d6d1688ecd9dc973f88
3
+ size 18025484864
Llama-3-Groq-70B-Tool-Use-Q6_K_L/Llama-3-Groq-70B-Tool-Use-Q6_K_L-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20071b3aa0695f98b489f11c8c7ddae7dcc445346eb0d045c924e9f23c4ae3b3
3
+ size 39924535200
Llama-3-Groq-70B-Tool-Use-Q6_K_L/Llama-3-Groq-70B-Tool-Use-Q6_K_L-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce82c5c14a05d0cc6c69ebf797ea022467cedd12021435950e8f354c1a2db3bb
3
+ size 18472632576
Llama-3-Groq-70B-Tool-Use-Q8_0/Llama-3-Groq-70B-Tool-Use-Q8_0-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cbf2f0c29873f6ffa6f8522de30105f4f38799494516015eeb436d7593325ce
3
+ size 39808988320
Llama-3-Groq-70B-Tool-Use-Q8_0/Llama-3-Groq-70B-Tool-Use-Q8_0-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7900ef37ae44eb12918e43394ffabbd4741e21fce0df92436deffa43f4bf11
3
+ size 35166166016
Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00001-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fadbc62d681940ce0915015c9fd08ff278ab55a0cdfc757698bd4dff1d567957
3
+ size 39376446464
Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00002-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c28e495530b0b4ac59a418ba24f0b41bdcf7e9cd74ede102d47743d566280e3f
3
+ size 39863425280
Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00003-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28df81f86e74c9f3edd7c8e9ca8c226cac5c0ae144b3a7a14b908aab80b10c3e
3
+ size 39796316288
Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00004-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a54c3af12b253ffcee5d46e864c285cf3046886aac06f18b11a85aa8beb0e64
3
+ size 39192369472
Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00005-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea1e0ee200be26da17a2ce3d02f5910648fb534fcc638129578eac8eaaf6f7a6
3
+ size 39527847968
Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00006-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53b1a41d749f094bcc1d4f34f51579e2ca98ebf9b801ee6fc286a2699b41208
3
+ size 39192336640
Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00007-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd23d0f59e932e365bae5bff02b981e737eeb69f3d88559579c4c5944df407ff
3
+ size 39527880768
Llama-3-Groq-70B-Tool-Use-f32/Llama-3-Groq-70B-Tool-Use-f32-00008-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebab7e3b0e66dd549361fd0aa56b5d0a1c879fa0ccfa0e467ccb5da488b45391
3
+ size 5746459200
Llama-3-Groq-70B-Tool-Use.imatrix ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf7a15a426143d0fa1beabcf99d40215de63f2568a7fba322af79913cfc5ea8
3
+ size 24922298
README.md ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Groq/Llama-3-Groq-70B-Tool-Use
3
+ language:
4
+ - en
5
+ license: llama3
6
+ pipeline_tag: text-generation
7
+ tags:
8
+ - facebook
9
+ - meta
10
+ - pytorch
11
+ - llama
12
+ - llama-3
13
+ - groq
14
+ - tool-use
15
+ - function-calling
16
+ quantized_by: bartowski
17
+ ---
18
+
19
+ ## Llamacpp imatrix Quantizations of Llama-3-Groq-70B-Tool-Use
20
+
21
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3389">b3389</a> for quantization.
22
+
23
+ Original model: https://huggingface.co/Groq/Llama-3-Groq-70B-Tool-Use
24
+
25
+ All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
26
+
27
+ Run them in [LM Studio](https://lmstudio.ai/)
28
+
29
+ ## Prompt format
30
+
31
+ ```
32
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
33
+
34
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
35
+
36
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
37
+
38
+
39
+ ```
40
+
41
+ ## Download a file (not the whole branch) from below:
42
+
43
+ | Filename | Quant type | File Size | Split | Description |
44
+ | -------- | ---------- | --------- | ----- | ----------- |
45
+ | [Llama-3-Groq-70B-Tool-Use-f32.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/tree/main/Llama-3-Groq-70B-Tool-Use-f32) | f32 | 282.22GB | true | Full F32 weights. |
46
+ | [Llama-3-Groq-70B-Tool-Use-Q8_0.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/tree/main/Llama-3-Groq-70B-Tool-Use-Q8_0) | Q8_0 | 74.98GB | true | Extremely high quality, generally unneeded but max available quant. |
47
+ | [Llama-3-Groq-70B-Tool-Use-Q6_K_L.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/tree/main/Llama-3-Groq-70B-Tool-Use-Q6_K_L) | Q6_K_L | 58.40GB | true | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
48
+ | [Llama-3-Groq-70B-Tool-Use-Q6_K.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/tree/main/Llama-3-Groq-70B-Tool-Use-Q6_K) | Q6_K | 57.89GB | true | Very high quality, near perfect, *recommended*. |
49
+ | [Llama-3-Groq-70B-Tool-Use-Q5_K_L.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/tree/main/Llama-3-Groq-70B-Tool-Use-Q5_K_L) | Q5_K_L | 50.60GB | true | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
50
+ | [Llama-3-Groq-70B-Tool-Use-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/tree/main/Llama-3-Groq-70B-Tool-Use-Q5_K_M) | Q5_K_M | 49.95GB | true | High quality, *recommended*. |
51
+ | [Llama-3-Groq-70B-Tool-Use-Q5_K_S.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-Q5_K_S.gguf) | Q5_K_S | 48.66GB | false | High quality, *recommended*. |
52
+ | [Llama-3-Groq-70B-Tool-Use-Q4_K_L.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-Q4_K_L.gguf) | Q4_K_L | 43.30GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
53
+ | [Llama-3-Groq-70B-Tool-Use-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-Q4_K_M.gguf) | Q4_K_M | 42.52GB | false | Good quality, default size for must use cases, *recommended*. |
54
+ | [Llama-3-Groq-70B-Tool-Use-Q4_K_S.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-Q4_K_S.gguf) | Q4_K_S | 40.35GB | false | Slightly lower quality with more space savings, *recommended*. |
55
+ | [Llama-3-Groq-70B-Tool-Use-Q3_K_XL.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-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. |
56
+ | [Llama-3-Groq-70B-Tool-Use-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-IQ4_XS.gguf) | IQ4_XS | 37.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
57
+ | [Llama-3-Groq-70B-Tool-Use-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-Q3_K_L.gguf) | Q3_K_L | 37.14GB | false | Lower quality but usable, good for low RAM availability. |
58
+ | [Llama-3-Groq-70B-Tool-Use-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-Q3_K_M.gguf) | Q3_K_M | 34.27GB | false | Low quality. |
59
+ | [Llama-3-Groq-70B-Tool-Use-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-IQ3_M.gguf) | IQ3_M | 31.94GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
60
+ | [Llama-3-Groq-70B-Tool-Use-Q3_K_S.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-Q3_K_S.gguf) | Q3_K_S | 30.91GB | false | Low quality, not recommended. |
61
+ | [Llama-3-Groq-70B-Tool-Use-IQ3_XS.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-IQ3_XS.gguf) | IQ3_XS | 29.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
62
+ | [Llama-3-Groq-70B-Tool-Use-Q2_K_L.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-Q2_K_L.gguf) | Q2_K_L | 27.40GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
63
+ | [Llama-3-Groq-70B-Tool-Use-Q2_K.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-Q2_K.gguf) | Q2_K | 26.38GB | false | Very low quality but surprisingly usable. |
64
+ | [Llama-3-Groq-70B-Tool-Use-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-3-Groq-70B-Tool-Use-GGUF/blob/main/Llama-3-Groq-70B-Tool-Use-IQ2_M.gguf) | IQ2_M | 24.12GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
65
+
66
+ ## Credits
67
+
68
+ Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset
69
+
70
+ Thank you ZeroWw for the inspiration to experiment with embed/output
71
+
72
+ ## Downloading using huggingface-cli
73
+
74
+ First, make sure you have hugginface-cli installed:
75
+
76
+ ```
77
+ pip install -U "huggingface_hub[cli]"
78
+ ```
79
+
80
+ Then, you can target the specific file you want:
81
+
82
+ ```
83
+ huggingface-cli download bartowski/Llama-3-Groq-70B-Tool-Use-GGUF --include "Llama-3-Groq-70B-Tool-Use-Q4_K_M.gguf" --local-dir ./
84
+ ```
85
+
86
+ 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:
87
+
88
+ ```
89
+ huggingface-cli download bartowski/Llama-3-Groq-70B-Tool-Use-GGUF --include "Llama-3-Groq-70B-Tool-Use-Q8_0.gguf/*" --local-dir Llama-3-Groq-70B-Tool-Use-Q8_0
90
+ ```
91
+
92
+ You can either specify a new local-dir (Llama-3-Groq-70B-Tool-Use-Q8_0) or download them all in place (./)
93
+
94
+ ## Which file should I choose?
95
+
96
+ A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
97
+
98
+ 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.
99
+
100
+ 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.
101
+
102
+ 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.
103
+
104
+ Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
105
+
106
+ 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.
107
+
108
+ If you want to get more into the weeds, you can check out this extremely useful feature chart:
109
+
110
+ [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
111
+
112
+ 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.
113
+
114
+ 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.
115
+
116
+ 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.
117
+
118
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
119
+