|
--- |
|
language: |
|
- en |
|
library_name: transformers |
|
license: llama2 |
|
quantized_by: mradermacher |
|
--- |
|
## About |
|
|
|
weighted/imatrix quants of https://huggingface.co/sophosympatheia/Aurora-Nights-70B-v1.0 |
|
<!-- 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-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 14.9 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.6 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.7 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 25.8 | IQ3_XXS probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.3 | fast, lower quality | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-Q3_K_XS.gguf) | i1-Q3_K_XS | 28.6 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.2 | IQ3_XS probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.6 | IQ3_S probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.5 | IQ3_M probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.6 | almost as good as Q4_K_M | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.7 | fast, medium quality | |
|
| [GGUF](https://huggingface.co/mradermacher/Aurora-Nights-70B-v1.0-i1-GGUF/resolve/main/Aurora-Nights-70B-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 49.1 | best weighted quant | |
|
|
|
|
|
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 |
|
|
|
<!-- end --> |
|
|
