Hugging Face's logo

bartowski
/
airoboros-dpo-110b-3.3-GGUF

Text Generation
GGUF
Inference Endpoints
imatrix
conversational
Model card Files Community
bartowski commited on
Commit
53550b6
•
1 Parent(s): 8f2183c

Llamacpp quants

Browse files
Files changed (48) hide show
  1. .gitattributes +46 -0
  2. README.md +122 -0
  3. airoboros-dpo-110b-3.3-IQ1_M.gguf +3 -0
  4. airoboros-dpo-110b-3.3-IQ1_S.gguf +3 -0
  5. airoboros-dpo-110b-3.3-IQ2_M.gguf +3 -0
  6. airoboros-dpo-110b-3.3-IQ2_S.gguf +3 -0
  7. airoboros-dpo-110b-3.3-IQ2_XS.gguf +3 -0
  8. airoboros-dpo-110b-3.3-IQ2_XXS.gguf +3 -0
  9. airoboros-dpo-110b-3.3-IQ3_M.gguf +3 -0
  10. airoboros-dpo-110b-3.3-IQ3_S.gguf +3 -0
  11. airoboros-dpo-110b-3.3-IQ3_XS.gguf +3 -0
  12. airoboros-dpo-110b-3.3-IQ3_XXS.gguf +3 -0
  13. airoboros-dpo-110b-3.3-IQ4_NL.gguf/airoboros-dpo-110b-3.3-IQ4_NL-00001-of-00002.gguf +3 -0
  14. airoboros-dpo-110b-3.3-IQ4_NL.gguf/airoboros-dpo-110b-3.3-IQ4_NL-00002-of-00002.gguf +3 -0
  15. airoboros-dpo-110b-3.3-IQ4_XS.gguf/airoboros-dpo-110b-3.3-IQ4_XS-00001-of-00002.gguf +3 -0
  16. airoboros-dpo-110b-3.3-IQ4_XS.gguf/airoboros-dpo-110b-3.3-IQ4_XS-00002-of-00002.gguf +3 -0
  17. airoboros-dpo-110b-3.3-Q2_K.gguf +3 -0
  18. airoboros-dpo-110b-3.3-Q3_K_L.gguf/airoboros-dpo-110b-3.3-Q3_K_L-00001-of-00002.gguf +3 -0
  19. airoboros-dpo-110b-3.3-Q3_K_L.gguf/airoboros-dpo-110b-3.3-Q3_K_L-00002-of-00002.gguf +3 -0
  20. airoboros-dpo-110b-3.3-Q3_K_M.gguf/airoboros-dpo-110b-3.3-Q3_K_M-00001-of-00002.gguf +3 -0
  21. airoboros-dpo-110b-3.3-Q3_K_M.gguf/airoboros-dpo-110b-3.3-Q3_K_M-00002-of-00002.gguf +3 -0
  22. airoboros-dpo-110b-3.3-Q3_K_S.gguf +3 -0
  23. airoboros-dpo-110b-3.3-Q4_K_M.gguf/airoboros-dpo-110b-3.3-Q4_K_M-00001-of-00003.gguf +3 -0
  24. airoboros-dpo-110b-3.3-Q4_K_M.gguf/airoboros-dpo-110b-3.3-Q4_K_M-00002-of-00003.gguf +3 -0
  25. airoboros-dpo-110b-3.3-Q4_K_M.gguf/airoboros-dpo-110b-3.3-Q4_K_M-00003-of-00003.gguf +3 -0
  26. airoboros-dpo-110b-3.3-Q4_K_S.gguf/airoboros-dpo-110b-3.3-Q4_K_S-00001-of-00002.gguf +3 -0
  27. airoboros-dpo-110b-3.3-Q4_K_S.gguf/airoboros-dpo-110b-3.3-Q4_K_S-00002-of-00002.gguf +3 -0
  28. airoboros-dpo-110b-3.3-Q5_K_M.gguf/airoboros-dpo-110b-3.3-Q5_K_M-00001-of-00003.gguf +3 -0
  29. airoboros-dpo-110b-3.3-Q5_K_M.gguf/airoboros-dpo-110b-3.3-Q5_K_M-00002-of-00003.gguf +3 -0
  30. airoboros-dpo-110b-3.3-Q5_K_M.gguf/airoboros-dpo-110b-3.3-Q5_K_M-00003-of-00003.gguf +3 -0
  31. airoboros-dpo-110b-3.3-Q5_K_S.gguf/airoboros-dpo-110b-3.3-Q5_K_S-00001-of-00003.gguf +3 -0
  32. airoboros-dpo-110b-3.3-Q5_K_S.gguf/airoboros-dpo-110b-3.3-Q5_K_S-00002-of-00003.gguf +3 -0
  33. airoboros-dpo-110b-3.3-Q5_K_S.gguf/airoboros-dpo-110b-3.3-Q5_K_S-00003-of-00003.gguf +3 -0
  34. airoboros-dpo-110b-3.3-Q6_K.gguf/airoboros-dpo-110b-3.3-Q6_K-00001-of-00003.gguf +3 -0
  35. airoboros-dpo-110b-3.3-Q6_K.gguf/airoboros-dpo-110b-3.3-Q6_K-00002-of-00003.gguf +3 -0
  36. airoboros-dpo-110b-3.3-Q6_K.gguf/airoboros-dpo-110b-3.3-Q6_K-00003-of-00003.gguf +3 -0
  37. airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00001-of-00004.gguf +3 -0
  38. airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00002-of-00004.gguf +3 -0
  39. airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00003-of-00004.gguf +3 -0
  40. airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00004-of-00004.gguf +3 -0
  41. airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00001-of-00007.gguf +3 -0
  42. airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00002-of-00007.gguf +3 -0
  43. airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00003-of-00007.gguf +3 -0
  44. airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00004-of-00007.gguf +3 -0
  45. airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00005-of-00007.gguf +3 -0
  46. airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00006-of-00007.gguf +3 -0
  47. airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00007-of-00007.gguf +3 -0
  48. airoboros-dpo-110b-3.3.imatrix +3 -0
.gitattributes CHANGED
@@ -33,3 +33,49 @@ 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
+ airoboros-dpo-110b-3.3-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ airoboros-dpo-110b-3.3-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ airoboros-dpo-110b-3.3-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ airoboros-dpo-110b-3.3-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ airoboros-dpo-110b-3.3-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
41
+ airoboros-dpo-110b-3.3-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
42
+ airoboros-dpo-110b-3.3-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ airoboros-dpo-110b-3.3-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ airoboros-dpo-110b-3.3-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
45
+ airoboros-dpo-110b-3.3-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
46
+ airoboros-dpo-110b-3.3-IQ4_NL.gguf/airoboros-dpo-110b-3.3-IQ4_NL-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
47
+ airoboros-dpo-110b-3.3-IQ4_NL.gguf/airoboros-dpo-110b-3.3-IQ4_NL-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
48
+ airoboros-dpo-110b-3.3-IQ4_XS.gguf/airoboros-dpo-110b-3.3-IQ4_XS-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
49
+ airoboros-dpo-110b-3.3-IQ4_XS.gguf/airoboros-dpo-110b-3.3-IQ4_XS-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
50
+ airoboros-dpo-110b-3.3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ airoboros-dpo-110b-3.3-Q3_K_L.gguf/airoboros-dpo-110b-3.3-Q3_K_L-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
52
+ airoboros-dpo-110b-3.3-Q3_K_L.gguf/airoboros-dpo-110b-3.3-Q3_K_L-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
53
+ airoboros-dpo-110b-3.3-Q3_K_M.gguf/airoboros-dpo-110b-3.3-Q3_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
54
+ airoboros-dpo-110b-3.3-Q3_K_M.gguf/airoboros-dpo-110b-3.3-Q3_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
55
+ airoboros-dpo-110b-3.3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
56
+ airoboros-dpo-110b-3.3-Q4_K_M.gguf/airoboros-dpo-110b-3.3-Q4_K_M-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
57
+ airoboros-dpo-110b-3.3-Q4_K_M.gguf/airoboros-dpo-110b-3.3-Q4_K_M-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
58
+ airoboros-dpo-110b-3.3-Q4_K_M.gguf/airoboros-dpo-110b-3.3-Q4_K_M-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
59
+ airoboros-dpo-110b-3.3-Q4_K_S.gguf/airoboros-dpo-110b-3.3-Q4_K_S-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
60
+ airoboros-dpo-110b-3.3-Q4_K_S.gguf/airoboros-dpo-110b-3.3-Q4_K_S-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
61
+ airoboros-dpo-110b-3.3-Q5_K_M.gguf/airoboros-dpo-110b-3.3-Q5_K_M-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
62
+ airoboros-dpo-110b-3.3-Q5_K_M.gguf/airoboros-dpo-110b-3.3-Q5_K_M-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
63
+ airoboros-dpo-110b-3.3-Q5_K_M.gguf/airoboros-dpo-110b-3.3-Q5_K_M-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
64
+ airoboros-dpo-110b-3.3-Q5_K_S.gguf/airoboros-dpo-110b-3.3-Q5_K_S-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
65
+ airoboros-dpo-110b-3.3-Q5_K_S.gguf/airoboros-dpo-110b-3.3-Q5_K_S-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
66
+ airoboros-dpo-110b-3.3-Q5_K_S.gguf/airoboros-dpo-110b-3.3-Q5_K_S-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
67
+ airoboros-dpo-110b-3.3-Q6_K.gguf/airoboros-dpo-110b-3.3-Q6_K-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
68
+ airoboros-dpo-110b-3.3-Q6_K.gguf/airoboros-dpo-110b-3.3-Q6_K-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
69
+ airoboros-dpo-110b-3.3-Q6_K.gguf/airoboros-dpo-110b-3.3-Q6_K-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
70
+ airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00001-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
71
+ airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00002-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
72
+ airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00003-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
73
+ airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00004-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
74
+ airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00001-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
75
+ airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00002-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
76
+ airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00003-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
77
+ airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00004-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
78
+ airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00005-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
79
+ airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00006-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
80
+ airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00007-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
81
+ airoboros-dpo-110b-3.3.imatrix filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: tongyi-qianwen
4
+ license_link: https://huggingface.co/Qwen/Qwen1.5-110B/blob/main/LICENSE
5
+ datasets:
6
+ - jondurbin/airoboros-3.2
7
+ - bluemoon-fandom-1-1-rp-cleaned
8
+ - boolq
9
+ - LDJnr/Capybara
10
+ - jondurbin/cinematika-v0.1
11
+ - glaiveai/glaive-function-calling-v2
12
+ - grimulkan/LimaRP-augmented
13
+ - piqa
14
+ - Vezora/Tested-22k-Python-Alpaca
15
+ - mattpscott/airoboros-summarization
16
+ - unalignment/toxic-dpo-v0.2
17
+ - allenai/ultrafeedback_binarized_cleaned
18
+ - argilla/distilabel-intel-orca-dpo-pairs
19
+ - jondurbin/airoboros-3.2
20
+ - jondurbin/contextual-dpo-v0.1
21
+ - jondurbin/gutenberg-dpo-v0.1
22
+ - jondurbin/py-dpo-v0.1
23
+ - jondurbin/truthy-dpo-v0.1
24
+ - jondurbin/gutenberg-dpo-v0.1
25
+ - lmsys/lmsys-chat-1m
26
+ quantized_by: bartowski
27
+ pipeline_tag: text-generation
28
+ ---
29
+
30
+ ## Llamacpp imatrix Quantizations of airoboros-dpo-110b-3.3
31
+
32
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2901">b2901</a> for quantization.
33
+
34
+ Original model: https://huggingface.co/jondurbin/airoboros-dpo-110b-3.3
35
+
36
+ All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/b6ac44691e994344625687afe3263b3a)
37
+
38
+ ## Prompt format
39
+
40
+ ```
41
+ <|im_start|>system
42
+ {system_prompt}<|im_end|>
43
+ <|im_start|>user
44
+ {prompt}<|im_end|>
45
+ <|im_start|>assistant
46
+
47
+ ```
48
+
49
+ ## Download a file (not the whole branch) from below:
50
+
51
+ | Filename | Quant type | File Size | Description |
52
+ | -------- | ---------- | --------- | ----------- |
53
+ | [airoboros-dpo-110b-3.3-Q8_0.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/tree/main/airoboros-dpo-110b-3.3-Q8_0.gguf) | Q8_0 | 118.17GB | Extremely high quality, generally unneeded but max available quant. |
54
+ | [airoboros-dpo-110b-3.3-Q6_K.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/tree/main/airoboros-dpo-110b-3.3-Q6_K.gguf) | Q6_K | 91.23GB | Very high quality, near perfect, *recommended*. |
55
+ | [airoboros-dpo-110b-3.3-Q5_K_M.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/tree/main/airoboros-dpo-110b-3.3-Q5_K_M.gguf) | Q5_K_M | 78.81GB | High quality, *recommended*. |
56
+ | [airoboros-dpo-110b-3.3-Q5_K_S.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/tree/main/airoboros-dpo-110b-3.3-Q5_K_S.gguf) | Q5_K_S | 76.63GB | High quality, *recommended*. |
57
+ | [airoboros-dpo-110b-3.3-Q4_K_M.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/tree/main/airoboros-dpo-110b-3.3-Q4_K_M.gguf) | Q4_K_M | 67.17GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
58
+ | [airoboros-dpo-110b-3.3-Q4_K_S.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/tree/main/airoboros-dpo-110b-3.3-Q4_K_S.gguf) | Q4_K_S | 63.47GB | Slightly lower quality with more space savings, *recommended*. |
59
+ | [airoboros-dpo-110b-3.3-IQ4_NL.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/tree/main/airoboros-dpo-110b-3.3-IQ4_NL.gguf) | IQ4_NL | 62.97GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
60
+ | [airoboros-dpo-110b-3.3-IQ4_XS.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/tree/main/airoboros-dpo-110b-3.3-IQ4_XS.gguf) | IQ4_XS | 59.55GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
61
+ | [airoboros-dpo-110b-3.3-Q3_K_L.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/tree/main/airoboros-dpo-110b-3.3-Q3_K_L.gguf) | Q3_K_L | 58.14GB | Lower quality but usable, good for low RAM availability. |
62
+ | [airoboros-dpo-110b-3.3-Q3_K_M.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/tree/main/airoboros-dpo-110b-3.3-Q3_K_M.gguf) | Q3_K_M | 53.70GB | Even lower quality. |
63
+ | [airoboros-dpo-110b-3.3-IQ3_M.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-IQ3_M.gguf) | IQ3_M | 49.70GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
64
+ | [airoboros-dpo-110b-3.3-IQ3_S.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-IQ3_S.gguf) | IQ3_S | 48.45GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
65
+ | [airoboros-dpo-110b-3.3-Q3_K_S.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-Q3_K_S.gguf) | Q3_K_S | 48.45GB | Low quality, not recommended. |
66
+ | [airoboros-dpo-110b-3.3-IQ3_XS.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-IQ3_XS.gguf) | IQ3_XS | 45.91GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
67
+ | [airoboros-dpo-110b-3.3-IQ3_XXS.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-IQ3_XXS.gguf) | IQ3_XXS | 43.10GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
68
+ | [airoboros-dpo-110b-3.3-Q2_K.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-Q2_K.gguf) | Q2_K | 41.17GB | Very low quality but surprisingly usable. |
69
+ | [airoboros-dpo-110b-3.3-IQ2_M.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-IQ2_M.gguf) | IQ2_M | 37.41GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
70
+ | [airoboros-dpo-110b-3.3-IQ2_S.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-IQ2_S.gguf) | IQ2_S | 34.33GB | Very low quality, uses SOTA techniques to be usable. |
71
+ | [airoboros-dpo-110b-3.3-IQ2_XS.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-IQ2_XS.gguf) | IQ2_XS | 33.04GB | Very low quality, uses SOTA techniques to be usable. |
72
+ | [airoboros-dpo-110b-3.3-IQ2_XXS.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-IQ2_XXS.gguf) | IQ2_XXS | 29.79GB | Lower quality, uses SOTA techniques to be usable. |
73
+ | [airoboros-dpo-110b-3.3-IQ1_M.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-IQ1_M.gguf) | IQ1_M | 25.94GB | Extremely low quality, *not* recommended. |
74
+ | [airoboros-dpo-110b-3.3-IQ1_S.gguf](https://huggingface.co/bartowski/airoboros-dpo-110b-3.3-GGUF/blob/main/airoboros-dpo-110b-3.3-IQ1_S.gguf) | IQ1_S | 23.63GB | Extremely low quality, *not* recommended. |
75
+
76
+ ## Downloading using huggingface-cli
77
+
78
+ First, make sure you have hugginface-cli installed:
79
+
80
+ ```
81
+ pip install -U "huggingface_hub[cli]"
82
+ ```
83
+
84
+ Then, you can target the specific file you want:
85
+
86
+ ```
87
+ huggingface-cli download bartowski/airoboros-dpo-110b-3.3-GGUF --include "airoboros-dpo-110b-3.3-Q4_K_M.gguf" --local-dir ./ --local-dir-use-symlinks False
88
+ ```
89
+
90
+ 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:
91
+
92
+ ```
93
+ huggingface-cli download bartowski/airoboros-dpo-110b-3.3-GGUF --include "airoboros-dpo-110b-3.3-Q8_0.gguf/*" --local-dir airoboros-dpo-110b-3.3-Q8_0 --local-dir-use-symlinks False
94
+ ```
95
+
96
+ You can either specify a new local-dir (airoboros-dpo-110b-3.3-Q8_0) or download them all in place (./)
97
+
98
+ ## Which file should I choose?
99
+
100
+ A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
101
+
102
+ 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.
103
+
104
+ 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.
105
+
106
+ 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.
107
+
108
+ Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
109
+
110
+ 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.
111
+
112
+ If you want to get more into the weeds, you can check out this extremely useful feature chart:
113
+
114
+ [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
115
+
116
+ 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.
117
+
118
+ 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.
119
+
120
+ 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.
121
+
122
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
airoboros-dpo-110b-3.3-IQ1_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae596fa827ebdd9b4988f94541ca0c69a284747547df9eb52cb962fe82c2b47
3
+ size 25942219520
airoboros-dpo-110b-3.3-IQ1_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8073150e878b054be855562f739b81f8429a191b35b82110b41375a371a2bdb
3
+ size 23630109440
airoboros-dpo-110b-3.3-IQ2_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d6376975e51e987d8d55f5be2bb42fb577ad1844fafa004740b10950ae88531
3
+ size 37419571968
airoboros-dpo-110b-3.3-IQ2_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016ddf55551685df7c82e99cfc75c5a34654ffc27f26bca899e3ac10d0f66bcf
3
+ size 34336758528
airoboros-dpo-110b-3.3-IQ2_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a8cc4cd6be42defa6e927650820e99f7d03ba16e3b53431efb5538a512a7220
3
+ size 33046321920
airoboros-dpo-110b-3.3-IQ2_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642918a2c601cc27d3c0f49dcf6571cb364daf93556d1e4650d7a08cca9c5f22
3
+ size 29795736320
airoboros-dpo-110b-3.3-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e247de91291dc200c06f03b4f93e16e62e90fee00170c0df5979e95ddd6a042d
3
+ size 49706556160
airoboros-dpo-110b-3.3-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af7673f3cdde89b33e8e0a2987d6da81a70293073342b63c2bad8ad9a2d7294
3
+ size 48458750720
airoboros-dpo-110b-3.3-IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3115c4e21c25ab7daf529675c77f6bfa96ce232a920e8605b1ce3a17b7129cbc
3
+ size 45910711040
airoboros-dpo-110b-3.3-IQ3_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b2051ca8720964d14292a7326496e073dd0958d8f7d810b792d131b1f05f434
3
+ size 43102853888
airoboros-dpo-110b-3.3-IQ4_NL.gguf/airoboros-dpo-110b-3.3-IQ4_NL-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b100330eeef4b4e927d494356a00b14baff9528b3a3d86b638d1346d4e4a1e82
3
+ size 32094917120
airoboros-dpo-110b-3.3-IQ4_NL.gguf/airoboros-dpo-110b-3.3-IQ4_NL-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9b36578050ca164472834252290296dc7f3bf4919890309c7cfd05d42eddd0
3
+ size 30879041984
airoboros-dpo-110b-3.3-IQ4_XS.gguf/airoboros-dpo-110b-3.3-IQ4_XS-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10dbf3f07d85086c083a262245bf893a21ae62e86a3053a97b4f975391ac522d
3
+ size 32067811680
airoboros-dpo-110b-3.3-IQ4_XS.gguf/airoboros-dpo-110b-3.3-IQ4_XS-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd266b01e9da7f03c74268076891283743e93e9e65f3a9e3cf5fc492cd7fa60a
3
+ size 27490804320
airoboros-dpo-110b-3.3-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd0d3724a5267bb1d49226be89f8077e7f252ec1e1051a1ed5596a0883b4efa
3
+ size 41175702272
airoboros-dpo-110b-3.3-Q3_K_L.gguf/airoboros-dpo-110b-3.3-Q3_K_L-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38498f7ed233299790662c0ef26f0da09f68e26fe8ef37083d4c71ab0ccf046
3
+ size 32196926560
airoboros-dpo-110b-3.3-Q3_K_L.gguf/airoboros-dpo-110b-3.3-Q3_K_L-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab852f82b324c777edc782e2aa5b9a754693fa6b931a74bba7d25307af3af0a
3
+ size 25950666592
airoboros-dpo-110b-3.3-Q3_K_M.gguf/airoboros-dpo-110b-3.3-Q3_K_M-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca2a6dbd14bf9dde4944760610b45ee4bb28c3837e4b006c998642a00f605c4
3
+ size 32174024416
airoboros-dpo-110b-3.3-Q3_K_M.gguf/airoboros-dpo-110b-3.3-Q3_K_M-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530545d6083db6b391788c4ddd7a73099a588baf9d60f6bf45012674d336c730
3
+ size 21527606496
airoboros-dpo-110b-3.3-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b60e85f909dadc05a321cf2419b5ff101f2fa0c05f96445c23205a86c87f0dcd
3
+ size 48458750720
airoboros-dpo-110b-3.3-Q4_K_M.gguf/airoboros-dpo-110b-3.3-Q4_K_M-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90e57c0925c6c1a03eff60c94a48180dd5e1c73714d567f258ee8db7182090ba
3
+ size 32018279040
airoboros-dpo-110b-3.3-Q4_K_M.gguf/airoboros-dpo-110b-3.3-Q4_K_M-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6ca3bb4f16bf0099f4d71718ca87f76d3c0b131377fe2173a47ed8e43b07fa
3
+ size 32059386656
airoboros-dpo-110b-3.3-Q4_K_M.gguf/airoboros-dpo-110b-3.3-Q4_K_M-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a6a220191c1efa6a7fae47b9a8ac2521f98b2f5772be62344f5edd739775f79
3
+ size 3093219008
airoboros-dpo-110b-3.3-Q4_K_S.gguf/airoboros-dpo-110b-3.3-Q4_K_S-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3834c911b3793b11bc61d7b846f3a14ac2d3459958d5be61ba0517688a174e84
3
+ size 32145215840
airoboros-dpo-110b-3.3-Q4_K_S.gguf/airoboros-dpo-110b-3.3-Q4_K_S-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698de8833c117cfe9f10094fe7567bb5628947f341a0b18fdc02d89d01442f46
3
+ size 31332059744
airoboros-dpo-110b-3.3-Q5_K_M.gguf/airoboros-dpo-110b-3.3-Q5_K_M-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a1d2eda0ed782948f474ef7ee25420e37d51a14d689c9eb8400f3b1142f192d
3
+ size 32071547872
airoboros-dpo-110b-3.3-Q5_K_M.gguf/airoboros-dpo-110b-3.3-Q5_K_M-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ce4c205778979d977229026e4a60d0ae35b3bae05fbd4afed47af86177fef51
3
+ size 31989037600
airoboros-dpo-110b-3.3-Q5_K_M.gguf/airoboros-dpo-110b-3.3-Q5_K_M-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e36576e3ea3570edfa35b9efba56b9a8aee553511613e25bfbbbdcb9980c9bd9
3
+ size 14758405696
airoboros-dpo-110b-3.3-Q5_K_S.gguf/airoboros-dpo-110b-3.3-Q5_K_S-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa10ca69b784c1731fd0dfc26f93da7945bcc97a28bcba648bd41dd032600c26
3
+ size 31973997760
airoboros-dpo-110b-3.3-Q5_K_S.gguf/airoboros-dpo-110b-3.3-Q5_K_S-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a80f31f32c6b17eb3ff24c42c41c190cd72ffbb407dbf5c11f3857e85cecc7
3
+ size 32149913056
airoboros-dpo-110b-3.3-Q5_K_S.gguf/airoboros-dpo-110b-3.3-Q5_K_S-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba895ba9739f57ed61205afaa414f56ebfcd70f0c18dd7629b99951a7df45ca
3
+ size 12511420832
airoboros-dpo-110b-3.3-Q6_K.gguf/airoboros-dpo-110b-3.3-Q6_K-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:093591c59e7e035225ca74c4dd50c803c9045610055e5a69dbea1f271931d428
3
+ size 31913954976
airoboros-dpo-110b-3.3-Q6_K.gguf/airoboros-dpo-110b-3.3-Q6_K-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df984c274ec986059900aa9ce4885cdeb290d6385e9de30c395b286b7947910
3
+ size 32001060384
airoboros-dpo-110b-3.3-Q6_K.gguf/airoboros-dpo-110b-3.3-Q6_K-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56fe9a2700cbeab1f1b5663601e6dce5e372bbf656da66f85690fdd70c9587ad
3
+ size 27324653408
airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00001-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2611adabb70d930917a19adf929ffa9e56987842061a821d949acf6242a3c02
3
+ size 32081239168
airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00002-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33348f57f78d8b9a916883092aeced9228a682e98d2b22cf51249a492946aa7d
3
+ size 31928425824
airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00003-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1745fb3bba744501d0bf8e626b0f2af3e1a6b5f362ce6fcc49688e3d3881157
3
+ size 32195738592
airoboros-dpo-110b-3.3-Q8_0.gguf/airoboros-dpo-110b-3.3-Q8_0-00004-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8014e0a564da633b38a2956af2718b0f08defaabb7a78c95850bf6501ed72b61
3
+ size 21967398656
airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00001-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804e8bcda16085e532a2ffc2c1aaed1f82e889ccdce01f1fb23c1d1522e581f5
3
+ size 31892218240
airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00002-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2789f1896bcce72042c33986b847ea2afb245053d836e40b8a1fb5d044e64ed
3
+ size 32012131744
airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00003-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29533e80e84d4f6134becb360d0ac366fc6486c889cc58350664f5c6365d5ec
3
+ size 31810887808
airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00004-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6f762602e32fc83a603d35d84f36cbeed6137b14dce812646288454a0a2958
3
+ size 31810887808
airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00005-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc3a381d93c38852ddd12d7d356951aaeb2612bbafd9243c77af91a18fd6c0ea
3
+ size 31810822144
airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00006-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f88f2b0b8f0f234a2425f8ef4b6d9cfbbeb425722e7f87228868f9886869ea
3
+ size 31508823744
airoboros-dpo-110b-3.3-f16.gguf/airoboros-dpo-110b-3.3-f16-00007-of-00007.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9683885bd592bb011d8e28cbbc21e2c7d76b53e81366a4a92611682805ef3d79
3
+ size 31584321088
airoboros-dpo-110b-3.3.imatrix ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc566ba8de7be6dac462289815c0372e08f653572b716c0e3944049022025035
3
+ size 31475897