|
--- |
|
exported_from: ibivibiv/hydra-moe-120b |
|
language: |
|
- en |
|
library_name: transformers |
|
license: apache-2.0 |
|
quantized_by: mradermacher |
|
tags: |
|
- moe |
|
- moerge |
|
--- |
|
## About |
|
|
|
<!-- ### quantize_version: 1 --> |
|
<!-- ### output_tensor_quantised: 1 --> |
|
<!-- ### convert_type: --> |
|
<!-- ### vocab_type: --> |
|
static quants of https://huggingface.co/ibivibiv/hydra-moe-120b |
|
|
|
<!-- provided-files --> |
|
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. |
|
## Usage |
|
|
|
If you are unsure how to use GGUF files, refer to one of [TheBloke's |
|
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for |
|
more details, including on how to concatenate multi-part files. |
|
|
|
## Provided Quants |
|
|
|
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) |
|
|
|
| Link | Type | Size/GB | Notes | |
|
|:-----|:-----|--------:|:------| |
|
| [GGUF](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q2_K.gguf) | Q2_K | 41.6 | | |
|
| [GGUF](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q3_K_S.gguf) | Q3_K_S | 49.1 | | |
|
| [GGUF](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.IQ3_S.gguf) | IQ3_S | 49.2 | beats Q3_K* | |
|
| [PART 1](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.IQ3_M.gguf.part2of2) | IQ3_M | 50.1 | | |
|
| [PART 1](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q3_K_M.gguf.part2of2) | Q3_K_M | 54.5 | lower quality | |
|
| [PART 1](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q3_K_L.gguf.part2of2) | Q3_K_L | 59.1 | | |
|
| [PART 1](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q4_K_S.gguf.part2of2) | Q4_K_S | 64.7 | fast, recommended | |
|
| [PART 1](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q4_K_M.gguf.part2of2) | Q4_K_M | 68.8 | fast, recommended | |
|
| [PART 1](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q5_K_S.gguf.part2of2) | Q5_K_S | 78.3 | | |
|
| [PART 1](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q6_K.gguf.part2of2) | Q6_K | 93.3 | very good quality | |
|
| [PART 1](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/hydra-moe-120b-GGUF/resolve/main/hydra-moe-120b.Q8_0.gguf.part3of3) | Q8_0 | 120.9 | fast, best quality | |
|
|
|
|
|
Here is a handy graph by ikawrakow comparing some lower-quality quant |
|
types (lower is better): |
|
|
|
 |
|
|
|
And here are Artefact2's thoughts on the matter: |
|
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 |
|
|
|
## Thanks |
|
|
|
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting |
|
me use its servers and providing upgrades to my workstation to enable |
|
this work in my free time. |
|
|
|
<!-- end --> |
|
|
