|
|
--- |
|
|
base_model: MaziyarPanahi/Supreme-Smaug-230B-v0.1 |
|
|
language: |
|
|
- en |
|
|
library_name: transformers |
|
|
quantized_by: mradermacher |
|
|
--- |
|
|
## About |
|
|
|
|
|
<!-- ### quantize_version: 2 --> |
|
|
<!-- ### output_tensor_quantised: 1 --> |
|
|
<!-- ### convert_type: hf --> |
|
|
<!-- ### vocab_type: --> |
|
|
<!-- ### tags: nicoboss --> |
|
|
weighted/imatrix quants of https://huggingface.co/MaziyarPanahi/Supreme-Smaug-230B-v0.1 |
|
|
|
|
|
<!-- provided-files --> |
|
|
static quants are available at https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-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/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ1_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ1_M.gguf.part2of2) | i1-IQ1_M | 54.3 | mostly desperate | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q2_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q2_K_S.gguf.part2of2) | i1-Q2_K_S | 77.5 | very low quality | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ2_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ2_M.gguf.part2of2) | i1-IQ2_M | 78.7 | | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q2_K.gguf.part2of2) | i1-Q2_K | 84.8 | IQ3_XXS probably better | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ3_XXS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ3_XXS.gguf.part2of2) | i1-IQ3_XXS | 87.0 | lower quality | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ3_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ3_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ3_M.gguf.part3of3) | i1-IQ3_M | 104.6 | | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q3_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q3_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q3_K_M.gguf.part3of3) | i1-Q3_K_M | 111.2 | IQ3_S probably better | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ4_XS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ4_XS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-IQ4_XS.gguf.part3of3) | i1-IQ4_XS | 122.3 | | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q4_K_S.gguf.part3of3) | i1-Q4_K_S | 130.3 | optimal size/speed/quality | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q4_K_M.gguf.part3of3) | i1-Q4_K_M | 138.4 | fast, recommended | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q6_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q6_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q6_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF/resolve/main/Supreme-Smaug-230B-v0.1.i1-Q6_K.gguf.part4of4) | i1-Q6_K | 188.2 | 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 |
|
|
|
|
|
## FAQ / Model Request |
|
|
|
|
|
See https://huggingface.co/mradermacher/model_requests for some answers to |
|
|
questions you might have and/or if you want some other model quantized. |
|
|
|
|
|
## 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. |
|
|
|
|
|
<!-- end --> |
|
|
|
