mradermacher
commited on
Commit
•
9ebc7bc
1
Parent(s):
a9e5395
auto-patch README.md
Browse files
README.md
CHANGED
@@ -29,12 +29,18 @@ more details, including on how to concatenate multi-part files.
|
|
29 |
|
30 |
| Link | Type | Size/GB | Notes |
|
31 |
|:-----|:-----|--------:|:------|
|
|
|
32 |
| [GGUF](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q2_K.gguf) | i1-Q2_K | 43.7 | IQ3_XXS probably better |
|
|
|
|
|
33 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 51.1 | IQ3_XS probably better |
|
|
|
34 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 57.0 | IQ3_S probably better |
|
35 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 62.1 | IQ3_M probably better |
|
36 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 67.2 | optimal size/speed/quality |
|
37 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 71.0 | fast, medium quality |
|
|
|
|
|
38 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 97.0 | practically like static Q6_K |
|
39 |
|
40 |
|
@@ -46,4 +52,10 @@ types (lower is better):
|
|
46 |
And here are Artefact2's thoughts on the matter:
|
47 |
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
|
48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
<!-- end -->
|
|
|
29 |
|
30 |
| Link | Type | Size/GB | Notes |
|
31 |
|:-----|:-----|--------:|:------|
|
32 |
+
| [GGUF](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-IQ2_M.gguf) | i1-IQ2_M | 40.0 | |
|
33 |
| [GGUF](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q2_K.gguf) | i1-Q2_K | 43.7 | IQ3_XXS probably better |
|
34 |
+
| [GGUF](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 45.6 | fast, lower quality |
|
35 |
+
| [GGUF](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 48.4 | |
|
36 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 51.1 | IQ3_XS probably better |
|
37 |
+
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 51.3 | fast, beats Q3_K* |
|
38 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 57.0 | IQ3_S probably better |
|
39 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 62.1 | IQ3_M probably better |
|
40 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 67.2 | optimal size/speed/quality |
|
41 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 71.0 | fast, medium quality |
|
42 |
+
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 81.4 | |
|
43 |
+
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 83.6 | |
|
44 |
| [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 97.0 | practically like static Q6_K |
|
45 |
|
46 |
|
|
|
52 |
And here are Artefact2's thoughts on the matter:
|
53 |
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
|
54 |
|
55 |
+
## Thanks
|
56 |
+
|
57 |
+
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
|
58 |
+
me use its servers and providing upgrades to my workstation to enable
|
59 |
+
this work in my free time.
|
60 |
+
|
61 |
<!-- end -->
|