|
--- |
|
language: |
|
- en |
|
library_name: transformers |
|
license: llama2 |
|
quantized_by: mradermacher |
|
tags: |
|
- moe |
|
- moerge |
|
--- |
|
## About |
|
|
|
weighted quants of https://huggingface.co/ibivibiv/giant-hydra-moe-240b |
|
|
|
<!-- provided-files --> |
|
static quants are available at https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF |
|
## 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 | |
|
|:-----|:-----|--------:|:------| |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ1_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ1_S.gguf.split-ab) | i1-IQ1_S | 49.5 | for the desperate | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ2_XXS.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ2_XXS.gguf.split-ab) | i1-IQ2_XXS | 63.4 | | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ2_XS.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ2_XS.gguf.split-ab) | i1-IQ2_XS | 70.5 | | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ2_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ2_M.gguf.part2of2) | i1-IQ2_M | 79.2 | | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q2_K.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q2_K.gguf.split-ab) | i1-Q2_K | 87.6 | IQ3_XXS probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ3_XXS.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ3_XXS.gguf.split-ab) | i1-IQ3_XXS | 92.7 | fast, lower quality | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_XS.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_XS.gguf.split-ab) | i1-Q3_K_XS | 96.5 | | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ3_XS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ3_XS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ3_XS.gguf.part3of3) | i1-IQ3_XS | 97.4 | | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_S.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_S.gguf.split-ac) | i1-Q3_K_S | 103.5 | IQ3_XS probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ3_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ3_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-IQ3_S.gguf.part3of3) | i1-IQ3_S | 103.5 | fast, beats Q3_K* | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_M.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_M.gguf.split-ac) | i1-Q3_K_M | 114.8 | IQ3_S probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_L.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q3_K_L.gguf.split-ac) | i1-Q3_K_L | 124.3 | IQ3_M probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q4_K_S.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q4_K_S.gguf.split-ac) | i1-Q4_K_S | 136.2 | optimal size/speed/quality | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q4_K_M.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q4_K_M.gguf.split-ac) | i1-Q4_K_M | 144.8 | fast, medium quality | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q5_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q5_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q5_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q5_K_S.gguf.part4of4) | i1-Q5_K_S | 164.7 | | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q5_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q5_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q5_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q5_K_M.gguf.part4of4) | i1-Q5_K_M | 169.7 | | |
|
| [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q6_K.gguf.part1of5) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q6_K.gguf.part2of5) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q6_K.gguf.part3of5) [PART 4](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q6_K.gguf.part4of5) [PART 5](https://huggingface.co/mradermacher/giant-hydra-moe-240b-i1-GGUF/resolve/main/giant-hydra-moe-240b.i1-Q6_K.gguf.part5of5) | i1-Q6_K | 196.3 | practically like static Q6_K | |
|
|
|
|
|
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 --> |
|
|
