Hugging Face's logo

featherless-ai-quants
/
nvidia-Llama3-ChatQA-1.5-70B-GGUF

Text Generation
GGUF
conversational
Model card Files
xet
 Community
m8than commited on
Commit
d27f836
·
verified ·
1 Parent(s): 6455beb

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +104 -0
  2. README.md +47 -0
  3. featherless-quants.png +3 -0
  4. nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00001-of-00008.gguf +3 -0
  5. nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00002-of-00008.gguf +3 -0
  6. nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00003-of-00008.gguf +3 -0
  7. nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00004-of-00008.gguf +3 -0
  8. nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00005-of-00008.gguf +3 -0
  9. nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00006-of-00008.gguf +3 -0
  10. nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00007-of-00008.gguf +3 -0
  11. nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00008-of-00008.gguf +3 -0
  12. nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00001-of-00006.gguf +3 -0
  13. nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00002-of-00006.gguf +3 -0
  14. nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00003-of-00006.gguf +3 -0
  15. nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00004-of-00006.gguf +3 -0
  16. nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00005-of-00006.gguf +3 -0
  17. nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00006-of-00006.gguf +3 -0
  18. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00001-of-00008.gguf +3 -0
  19. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00002-of-00008.gguf +3 -0
  20. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00003-of-00008.gguf +3 -0
  21. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00004-of-00008.gguf +3 -0
  22. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00005-of-00008.gguf +3 -0
  23. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00006-of-00008.gguf +3 -0
  24. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00007-of-00008.gguf +3 -0
  25. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00008-of-00008.gguf +3 -0
  26. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00001-of-00007.gguf +3 -0
  27. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00002-of-00007.gguf +3 -0
  28. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00003-of-00007.gguf +3 -0
  29. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00004-of-00007.gguf +3 -0
  30. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00005-of-00007.gguf +3 -0
  31. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00006-of-00007.gguf +3 -0
  32. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00007-of-00007.gguf +3 -0
  33. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00001-of-00007.gguf +3 -0
  34. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00002-of-00007.gguf +3 -0
  35. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00003-of-00007.gguf +3 -0
  36. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00004-of-00007.gguf +3 -0
  37. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00005-of-00007.gguf +3 -0
  38. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00006-of-00007.gguf +3 -0
  39. nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00007-of-00007.gguf +3 -0
  40. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00001-of-00009.gguf +3 -0
  41. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00002-of-00009.gguf +3 -0
  42. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00003-of-00009.gguf +3 -0
  43. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00004-of-00009.gguf +3 -0
  44. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00005-of-00009.gguf +3 -0
  45. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00006-of-00009.gguf +3 -0
  46. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00007-of-00009.gguf +3 -0
  47. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00008-of-00009.gguf +3 -0
  48. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00009-of-00009.gguf +3 -0
  49. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00001-of-00009.gguf +3 -0
  50. nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00002-of-00009.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,107 @@ saved_model/**/* 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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ featherless-quants.png filter=lfs diff=lfs merge=lfs -text
37
+ nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00001-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
38
+ nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00002-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
39
+ nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00003-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
40
+ nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00004-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
41
+ nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00005-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
42
+ nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00006-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
43
+ nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00007-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
44
+ nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00008-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
45
+ nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
46
+ nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
47
+ nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
48
+ nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
49
+ nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
50
+ nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
51
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00001-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
52
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00002-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
53
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00003-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
54
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00004-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
55
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00005-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
56
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00006-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
57
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00007-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
58
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00008-of-00008.gguf filter=lfs diff=lfs merge=lfs -text
59
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00001-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
60
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00002-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
61
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00003-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
62
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00004-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
63
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00005-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
64
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00006-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
65
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00007-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
66
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00001-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
67
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00002-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
68
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00003-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
69
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00004-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
70
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00005-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
71
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00006-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
72
+ nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00007-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
73
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00001-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
74
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00002-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
75
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00003-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
76
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00004-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
77
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00005-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
78
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00006-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
79
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00007-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
80
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00008-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
81
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00009-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
82
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00001-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
83
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00002-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
84
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00003-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
85
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00004-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
86
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00005-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
87
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00006-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
88
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00007-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
89
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00008-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
90
+ nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00009-of-00009.gguf filter=lfs diff=lfs merge=lfs -text
91
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00001-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
92
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00002-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
93
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00003-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
94
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00004-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
95
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00005-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
96
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00006-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
97
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00007-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
98
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00008-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
99
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00009-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
100
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00010-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
101
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M-00011-of-00011.gguf filter=lfs diff=lfs merge=lfs -text
102
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S-00001-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
103
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S-00002-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
104
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S-00003-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
105
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S-00004-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
106
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S-00005-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
107
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S-00006-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
108
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S-00007-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
109
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S-00008-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
110
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S-00009-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
111
+ nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S-00010-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
112
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00001-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
113
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00002-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
114
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00003-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
115
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00004-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
116
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00005-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
117
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00006-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
118
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00007-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
119
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00008-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
120
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00009-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
121
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00010-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
122
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00011-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
123
+ nvidia-Llama3-ChatQA-1.5-70B-Q6_K/nvidia-Llama3-ChatQA-1.5-70B-Q6_K-00012-of-00012.gguf filter=lfs diff=lfs merge=lfs -text
124
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00001-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
125
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00002-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
126
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00003-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
127
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00004-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
128
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00005-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
129
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00006-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
130
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00007-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
131
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00008-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
132
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00009-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
133
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00010-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
134
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00011-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
135
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00012-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
136
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00013-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
137
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00014-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
138
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00015-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
139
+ nvidia-Llama3-ChatQA-1.5-70B-Q8_0/nvidia-Llama3-ChatQA-1.5-70B-Q8_0-00016-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: nvidia/Llama3-ChatQA-1.5-70B
3
+ pipeline_tag: text-generation
4
+ quantized_by: featherless-ai-quants
5
+ ---
6
+
7
+ # nvidia/Llama3-ChatQA-1.5-70B GGUF Quantizations 🚀
8
+
9
+ ![Featherless AI Quants](./featherless-quants.png)
10
+
11
+ *Optimized GGUF quantization files for enhanced model performance*
12
+
13
+ > Powered by [Featherless AI](https://featherless.ai) - run any model you'd like for a simple small fee.
14
+ ---
15
+
16
+ ## Available Quantizations 📊
17
+
18
+ | Quantization Type | File | Size |
19
+ |-------------------|------|------|
20
+ | IQ4_XS | [nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS) | 36496.80 MB (folder) |
21
+ | Q2_K | [nvidia-Llama3-ChatQA-1.5-70B-Q2_K](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-Q2_K) | 25153.26 MB (folder) |
22
+ | Q3_K_L | [nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L) | 35420.03 MB (folder) |
23
+ | Q3_K_M | [nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M) | 32680.03 MB (folder) |
24
+ | Q3_K_S | [nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S) | 29480.03 MB (folder) |
25
+ | Q4_K_M | [nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M) | 40550.61 MB (folder) |
26
+ | Q4_K_S | [nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S) | 38478.11 MB (folder) |
27
+ | Q5_K_M | [nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M) | 47635.86 MB (folder) |
28
+ | Q5_K_S | [nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S) | 46403.36 MB (folder) |
29
+ | Q6_K | [nvidia-Llama3-ChatQA-1.5-70B-Q6_K](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-Q6_K) | 55206.44 MB (folder) |
30
+ | Q8_0 | [nvidia-Llama3-ChatQA-1.5-70B-Q8_0](https://huggingface.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF/tree/main/nvidia-Llama3-ChatQA-1.5-70B-Q8_0) | 71501.78 MB (folder) |
31
+
32
+
33
+ ---
34
+
35
+ ## ⚡ Powered by [Featherless AI](https://featherless.ai)
36
+
37
+ ### Key Features
38
+
39
+ - 🔥 **Instant Hosting** - Deploy any Llama model on HuggingFace instantly
40
+ - 🛠️ **Zero Infrastructure** - No server setup or maintenance required
41
+ - 📚 **Vast Compatibility** - Support for 2400+ models and counting
42
+ - 💎 **Affordable Pricing** - Starting at just $10/month
43
+
44
+ ---
45
+
46
+ **Links:**
47
+ [Get Started](https://featherless.ai) | [Documentation](https://featherless.ai/docs) | [Models](https://featherless.ai/models)
featherless-quants.png ADDED

Git LFS Details

  • SHA256: 2e1b4d66c8306c7b0614089381fdf86ea4efb02dffb78d22767a084cb8b88d6b
  • Pointer size: 132 Bytes
  • Size of remote file: 1.61 MB
nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00001-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f64ddf6dd775a0a29e9de6c52f927016b8aa8dab2981b1c1e72b781667f5f0
3
+ size 5004223488
nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00002-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe506900306a015a1d741765b5322779570d53ded0241d418392733ab3a0699
3
+ size 4970386976
nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00003-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efaab75c0841fa71fbea6cd3da51ca58e82bf6da4ec1333732274fd251044037
3
+ size 4886009568
nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00004-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffb030ce81e7c1cc6ceebb5b0c2c251a1784e51f8bb86c1a20a8b2615d3a32f2
3
+ size 4890498912
nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00005-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d0d88ab9f055f9aaaad653940316de62f56944c9aecc2ce3e0359afb62e200
3
+ size 4890498912
nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00006-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96965f81952f7079e6fa20456d54b78bb2932571791a61196f6fe09ed500ec0d
3
+ size 4973827808
nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00007-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf08867de0344f427e0d1cbd959cdf29852d4728b846faa0d17e38a9457481f
3
+ size 4931917792
nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00008-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f1817f8e8d069d707a3555bc47c51a7e20c9e4ed8216379c6c44acc41b779b1
3
+ size 3722300864
nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00001-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbebb4a39f765f38a2daed698e45ddc386c235a16eeb6d2134fee06e8cb5344e
3
+ size 4933709440
nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00002-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d711264f32b5a0aa628198b1f8c91cf67f828d6fc87c8b251ec4757116d5aa99
3
+ size 4955054560
nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00003-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7ee50b4974db4405e314794c0d19b54fff7a3fd741f3bff21f370855873c1e
3
+ size 4931199456
nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00004-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6827adf0ccbafa123c8f320e500195a6f88d0abd4a80003de35b10616edc21d
3
+ size 4975468832
nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00005-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016a46b4174f0a5e68a967c7e054da37dfdaf12e34997036d62aaa9b3792bed3
3
+ size 4952269152
nvidia-Llama3-ChatQA-1.5-70B-Q2_K/nvidia-Llama3-ChatQA-1.5-70B-Q2_K-00006-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8424fdea3608b53cbf4ef990ff160192df43eed490fb08d9e7e68df40826e69
3
+ size 1627408000
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00001-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39ad1fea86a35de1c1ee959929596097093157e301b22f1e8448803811de16a
3
+ size 4986512992
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00002-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ede26fb10801bb4aa968d11da4b53f7cad99309fcf98986e08c50f866c01991
3
+ size 4976318240
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00003-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f71d01b54f35cf4136c6123769c20c8d92cde9a0079d590ca02609e0e1b19d0
3
+ size 4985722784
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00004-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cfaa18b8dde7bdd5b4a4a94d8aad06553db1be546cbd3816bbc7887610488a2
3
+ size 4925167520
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00005-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70c0868b6565211eef91222d032addcbd905c7d5d1f7b61b95309835c41246b8
3
+ size 4925167520
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00006-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ae2c6a10d762b4700191decd774c261b6eb8cc023c377e2bdc9f5f4db7fe8b
3
+ size 4925167520
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00007-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:969f89e19651c4f74995c0a9212edcdb46a9ce1b68af54ad38bedb87a06c68d2
3
+ size 4925167520
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L-00008-of-00008.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8adc0ab10ddd3369f0f8f9e5563a0abe37510c030821b9b2d30e312f9e080b62
3
+ size 2491369696
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00001-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dcc8c83804ec90e14cd847c8e7b32cef5dc304d360729b4966b6c63c602a5e1
3
+ size 4914161408
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00002-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61900b1b6c7fa05163b762ea15640f6373dcd210cec751a1db08532644edc02
3
+ size 4944861376
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00003-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d9da8a468f4204448737e9c00b8506652b997fe459066fc1ae9cc2a15df95dc
3
+ size 4919925184
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00004-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f6add205dd0216026565967eb719d0f956eff2c34eee76baad590200b06c13
3
+ size 4919925184
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00005-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4915ca59ac91f4d00a77c22e5fd430563f631d3945b037dd567c3d549c3a5f63
3
+ size 4919925184
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00006-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f7959cc24efb3237b313060f6ab7f5ebed4dd435bea42a29caa570812a95e1
3
+ size 4919925184
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M-00007-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e1375a9b9f13d3aeb45bb2a4c92c4d117ac2ab635fc2a9190aa08fb608084a
3
+ size 4728771904
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00001-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:373ae41dd6651f7e4f602fc2aeeb524c0f234c55d269c673699f81766b471980
3
+ size 4998867488
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00002-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd968f96b139c5b7fbb781e35da97504332ac60ac403be1d2a0b02a2f9eafd4
3
+ size 4909440000
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00003-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfabfea38ffb7358b5b26561ce8ef989391fb87b59b4a610ba16980b8fd74088
3
+ size 4976549216
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00004-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4704dd531d42f52416de7d934b0fc27718c0b74aae8d5b6cd165ac695cfdd78c
3
+ size 4909440000
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00005-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:150f1b8c80e3b949d02ee05fb6ef27c094949fb8fbef1334c3a99260acc8e882
3
+ size 4909440000
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00006-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a8e44eed70e4943d89b8ad1689ffb264578fabd74931835b3a82d94ffd36bae
3
+ size 4980186592
nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S-00007-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9b42017df8cf27d75f957ff8e9f294264d893cbcc9e114b85da5e08f422717
3
+ size 1228128864
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00001-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9d48efbb1a702a5f723e81913288d6eae48d144f552d2a2030c51d2a1ee563
3
+ size 4993999424
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00002-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89150ca5091b777ce2d0e1ffdc2a601c47f23e51116255cd9fb36f92c884189d
3
+ size 4984738816
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00003-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13a188e00489d373e220dd660bc4ca19358c816e090b4a42439752aa73fff7e
3
+ size 4982183360
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00004-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea995e551ef362f32e4c2999cb2d39288bca5a22b6670ca16b2675a8f51f9a54
3
+ size 4923102304
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00005-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df72464bda183d18c5f5b9e5f18b0d85605c1523542dde68e175bb213ed2b5aa
3
+ size 4876997952
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00006-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e4bc37fbac77e2ab0ffc74f55f082e785674870712c1de9d75bf2e12f84800f
3
+ size 4876997952
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00007-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4bc36d67a1d6f2f4b0652a2598ec3b3eba284e6963c30ce47aa694c953edbc
3
+ size 4988376192
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00008-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:849b33a04842a2b78ced2a11acf4c852a4dbafe827ae5f20d188ed7b824cbae5
3
+ size 4855796832
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M-00009-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de163661b41829992dd6248a73a3116af4cf854ecbceee94df54443a30c6ade6
3
+ size 3038202144
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00001-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee1d2935780fd92e939b4d9d5434a750e0e3460089e99c876056d52ed4b9da0e
3
+ size 4940555040
nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S/nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S-00002-of-00009.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b31c42e5e2302f6e05a911843d4c72c47da17034c3bf3e2c3bef724e41b7beb
3
+ size 4899542080