|
--- |
|
language: |
|
- en |
|
library_name: transformers |
|
license: llama2 |
|
quantized_by: mradermacher |
|
--- |
|
## About |
|
|
|
weighted/imatrix wants of https://huggingface.co/sophosympatheia/Aurora-Nights-103B-v1.0 |
|
|
|
the weights were calculated using 164k semi-random english-only tokens. |
|
|
|
<!-- 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 | |
|
|:-----|:-----|--------:|:------| |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 22.1 | for the desperate | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.7 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.8 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 38.3 | IQ3_XXS probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 40.6 | fast, lower quality | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q3_K_XS.gguf) | i1-Q3_K_XS | 42.4 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 44.9 | IQ3_XS probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q3_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q3_K_M.gguf.split-ab) | i1-Q3_K_M | 50.0 | IQ3_S probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q3_K_L.gguf.split-ab) | i1-Q3_K_L | 54.5 | IQ3_M probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q4_K_S.gguf.split-ab) | i1-Q4_K_S | 59.0 | almost as good as Q4_K_M | |
|
| [PART 1](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q4_K_M.gguf.split-ab) | i1-Q4_K_M | 62.3 | fast, medium quality | |
|
| [PART 1](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Aurora-Nights-103B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-103B-v1.0.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 71.4 | | |
|
|
|
|
|
Here is a handy graph by ikawrakow comparing some lower-quality quant |
|
types (lower is better): |
|
|
|
![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) |
|
|
|
And here are Artefact2's thoughts on the matter: |
|
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 |
|
|
|
<!-- end --> |
|
|