Melusine_103b-GGUF / README.md
mradermacher's picture
auto-patch README.md
fc26202 verified
|
raw
history blame
2.41 kB
---
exported_from: MarsupialAI/Melusine_103b
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- rp
- erp
- chat
- miqu
---
## About
static quants of https://huggingface.co/MarsupialAI/Melusine_103b
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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/Melusine_103b-GGUF/resolve/main/Melusine_103b.IQ3_S.gguf) | IQ3_S | 45.0 | beats Q3_K* |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-GGUF/resolve/main/Melusine_103b.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-GGUF/resolve/main/Melusine_103b.Q3_K_M.gguf.part2of2) | Q3_K_M | 50.0 | lower quality |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-GGUF/resolve/main/Melusine_103b.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-GGUF/resolve/main/Melusine_103b.Q4_K_S.gguf.part2of2) | Q4_K_S | 59.0 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-GGUF/resolve/main/Melusine_103b.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-GGUF/resolve/main/Melusine_103b.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Melusine_103b-GGUF/resolve/main/Melusine_103b.Q8_0.gguf.part3of3) | Q8_0 | 110.0 | 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
## 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 -->