|
--- |
|
base_model: deepnight-research/Saily_220B |
|
datasets: |
|
- tiiuae/falcon-refinedweb |
|
- EleutherAI/pile |
|
- meta-math/MetaMathQA |
|
language: |
|
- en |
|
library_name: transformers |
|
license: llama2 |
|
no_imatrix: 'GGML_ASSERT: llama.cpp/ggml.c:16553: i != GGML_HASHTABLE_FULL' |
|
quantized_by: mradermacher |
|
--- |
|
## About |
|
|
|
static quants of https://huggingface.co/deepnight-research/Saily_220B |
|
|
|
<!-- provided-files --> |
|
## 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/Saily_220B-GGUF/resolve/main/Saily_220B.Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q2_K.gguf.part2of2) | Q2_K | 76.9 | | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.IQ3_XS.gguf.part2of2) | IQ3_XS | 85.5 | | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q3_K_S.gguf.part2of2) | Q3_K_S | 90.1 | | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.IQ3_S.gguf.part2of2) | IQ3_S | 90.4 | beats Q3_K* | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.IQ3_M.gguf.part2of2) | IQ3_M | 93.5 | | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q3_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q3_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q3_K_M.gguf.part3of3) | Q3_K_M | 100.6 | lower quality | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q3_K_L.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q3_K_L.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q3_K_L.gguf.part3of3) | Q3_K_L | 109.5 | | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.IQ4_XS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.IQ4_XS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.IQ4_XS.gguf.part3of3) | IQ4_XS | 112.7 | | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q4_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q4_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q4_0.gguf.part3of3) | Q4_0 | 117.7 | fast, low quality | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q4_K_S.gguf.part3of3) | Q4_K_S | 118.6 | fast, recommended | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q4_K_M.gguf.part3of3) | Q4_K_M | 125.3 | fast, recommended | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q5_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q5_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q5_K_S.gguf.part3of3) | Q5_K_S | 143.8 | | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q5_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q5_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q5_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q5_K_M.gguf.part4of4) | Q5_K_M | 147.7 | | |
|
| [PART 1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q6_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q6_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q6_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q6_K.gguf.part4of4) | Q6_K | 171.4 | very good quality | |
|
| [P1](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q8_0.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q8_0.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q8_0.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q8_0.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Saily_220B-GGUF/resolve/main/Saily_220B.Q8_0.gguf.part5of5) | Q8_0 | 221.8 | 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 |
|
|
|
## 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. |
|
|
|
<!-- end --> |
|
|
