|
--- |
|
base_model: BSC-LT/ALIA-40b |
|
datasets: |
|
- oscar-corpus/colossal-oscar-1.0 |
|
- HuggingFaceFW/fineweb-edu |
|
- joelniklaus/eurlex_resources |
|
- joelniklaus/legal-mc4 |
|
- projecte-aina/CATalog |
|
- UFRGS/brwac |
|
- community-datasets/hrwac |
|
- danish-foundation-models/danish-gigaword |
|
- HiTZ/euscrawl |
|
- PleIAs/French-PD-Newspapers |
|
- PleIAs/French-PD-Books |
|
- AI-team-UoA/greek_legal_code |
|
- HiTZ/latxa-corpus-v1.1 |
|
- allenai/peS2o |
|
- pile-of-law/pile-of-law |
|
- PORTULAN/parlamento-pt |
|
- hoskinson-center/proof-pile |
|
- togethercomputer/RedPajama-Data-1T |
|
- bigcode/starcoderdata |
|
- bjoernp/tagesschau-2018-2023 |
|
- EleutherAI/the_pile_deduplicated |
|
language: |
|
- bg |
|
- ca |
|
- code |
|
- cs |
|
- cy |
|
- da |
|
- de |
|
- el |
|
- en |
|
- es |
|
- et |
|
- eu |
|
- fi |
|
- fr |
|
- ga |
|
- gl |
|
- hr |
|
- hu |
|
- it |
|
- lt |
|
- lv |
|
- mt |
|
- nl |
|
- nn |
|
- \no |
|
- oc |
|
- pl |
|
- pt |
|
- ro |
|
- ru |
|
- sh |
|
- sk |
|
- sl |
|
- sr |
|
- sv |
|
- uk |
|
library_name: transformers |
|
license: apache-2.0 |
|
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/BSC-LT/ALIA-40b |
|
|
|
<!-- provided-files --> |
|
static quants are available at https://huggingface.co/mradermacher/ALIA-40b-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 | |
|
|:-----|:-----|--------:|:------| |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ1_S.gguf) | i1-IQ1_S | 9.8 | for the desperate | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ1_M.gguf) | i1-IQ1_M | 10.6 | mostly desperate | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 11.8 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.9 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ2_S.gguf) | i1-IQ2_S | 13.7 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ2_M.gguf) | i1-IQ2_M | 14.6 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 14.8 | very low quality | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q2_K.gguf) | i1-Q2_K | 15.8 | IQ3_XXS probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 16.3 | lower quality | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 17.5 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 18.3 | IQ3_XS probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ3_S.gguf) | i1-IQ3_S | 18.4 | beats Q3_K* | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ3_M.gguf) | i1-IQ3_M | 18.9 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 20.1 | IQ3_S probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 21.7 | IQ3_M probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 22.3 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q4_0.gguf) | i1-Q4_0 | 23.5 | fast, low quality | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 23.5 | optimal size/speed/quality | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 24.7 | fast, recommended | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q4_1.gguf) | i1-Q4_1 | 25.8 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 28.2 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 28.9 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ALIA-40b-i1-GGUF/resolve/main/ALIA-40b.i1-Q6_K.gguf) | i1-Q6_K | 33.3 | 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 |
|
|
|
## 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 --> |
|
|
