mradermacher's picture
auto-patch README.md
3090579 verified
|
raw
history blame
3.68 kB
---
base_model: Alsebay/FinalFintetuning-XVIII-2x8B
language:
- en
library_name: transformers
license: cc-by-nc-4.0
no_imatrix: nan
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hfhfix -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/Alsebay/FinalFintetuning-XVIII-2x8B
<!-- 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/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.Q2_K.gguf) | Q2_K | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.IQ3_XS.gguf) | IQ3_XS | 5.9 | |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.Q3_K_S.gguf) | Q3_K_S | 6.2 | |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.IQ3_S.gguf) | IQ3_S | 6.2 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.IQ3_M.gguf) | IQ3_M | 6.3 | |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.Q3_K_M.gguf) | Q3_K_M | 6.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.Q3_K_L.gguf) | Q3_K_L | 7.3 | |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.IQ4_XS.gguf) | IQ4_XS | 7.6 | |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.Q4_K_S.gguf) | Q4_K_S | 8.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.Q4_K_M.gguf) | Q4_K_M | 8.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.Q5_K_S.gguf) | Q5_K_S | 9.6 | |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.Q5_K_M.gguf) | Q5_K_M | 9.8 | |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.Q6_K.gguf) | Q6_K | 11.3 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/FinalFintetuning-XVIII-2x8B-GGUF/resolve/main/FinalFintetuning-XVIII-2x8B.Q8_0.gguf) | Q8_0 | 14.6 | fast, best quality |
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
## 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 -->