Transformers
English
Inference Endpoints
mradermacher commited on
Commit
09a6d3c
1 Parent(s): 78b4ed7

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -29,19 +29,19 @@ more details, including on how to concatenate multi-part files.
29
  |:-----|:-----|--------:|:------|
30
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q2_K.gguf.part2of2) | Q2_K | 67.8 | |
31
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_XS.gguf.part2of2) | IQ3_XS | 76.3 | |
32
- | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_S.gguf.part2of2) | IQ3_S | 78.8 | fast, beats Q3_K* |
33
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_S.gguf.part2of2) | Q3_K_S | 78.8 | |
34
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_M.gguf.part2of2) | IQ3_M | 82.4 | |
35
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_M.gguf.part2of2) | Q3_K_M | 86.5 | lower quality |
36
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_L.gguf.part2of2) | Q3_K_L | 93.0 | |
37
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ4_XS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ4_XS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ4_XS.gguf.part3of3) | IQ4_XS | 98.3 | |
38
- | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_S.gguf.part3of3) | Q4_K_S | 102.5 | fast, medium quality |
39
- | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_M.gguf.part3of3) | Q4_K_M | 109.8 | fast, medium quality |
40
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_S.gguf.part3of3) | Q5_K_S | 124.8 | |
41
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_M.gguf.part3of3) | Q5_K_M | 132.0 | |
42
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q6_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q6_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q6_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q6_K.gguf.part4of4) | Q6_K | 148.5 | very good quality |
43
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q8_0.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q8_0.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q8_0.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q8_0.gguf.part4of4) | Q8_0 | 191.8 | fast, best quality |
44
- | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part1of8) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part2of8) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part3of8) [PART 4](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part4of8) [PART 5](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part5of8) [PART 6](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part6of8) [PART 7](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part7of8) [PART 8](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part8of8) | SOURCE | 359.2 | source gguf, only provided when it was hard to come by |
45
 
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
29
  |:-----|:-----|--------:|:------|
30
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q2_K.gguf.part2of2) | Q2_K | 67.8 | |
31
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_XS.gguf.part2of2) | IQ3_XS | 76.3 | |
32
+ | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_S.gguf.part2of2) | IQ3_S | 78.8 | beats Q3_K* |
33
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_S.gguf.part2of2) | Q3_K_S | 78.8 | |
34
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ3_M.gguf.part2of2) | IQ3_M | 82.4 | |
35
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_M.gguf.part2of2) | Q3_K_M | 86.5 | lower quality |
36
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q3_K_L.gguf.part2of2) | Q3_K_L | 93.0 | |
37
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ4_XS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ4_XS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.IQ4_XS.gguf.part3of3) | IQ4_XS | 98.3 | |
38
+ | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_S.gguf.part3of3) | Q4_K_S | 102.5 | fast, recommended |
39
+ | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q4_K_M.gguf.part3of3) | Q4_K_M | 109.8 | fast, recommended |
40
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_S.gguf.part3of3) | Q5_K_S | 124.8 | |
41
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q5_K_M.gguf.part3of3) | Q5_K_M | 132.0 | |
42
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q6_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q6_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q6_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q6_K.gguf.part4of4) | Q6_K | 148.5 | very good quality |
43
  | [PART 1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q8_0.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q8_0.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q8_0.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.Q8_0.gguf.part4of4) | Q8_0 | 191.8 | fast, best quality |
44
+ | [P1](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part1of8) [P2](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part2of8) [P3](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part3of8) [P4](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part4of8) [P5](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part5of8) [P6](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part6of8) [P7](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part7of8) [P8](https://huggingface.co/mradermacher/airoboros-180b-2.2.1-GGUF/resolve/main/airoboros-180b-2.2.1.SOURCE.gguf.part8of8) | SOURCE | 359.2 | source gguf, only provided when it was hard to come by |
45
 
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant