mradermacher's picture
auto-patch README.md
08daa0b verified
|
raw
history blame
4.48 kB
---
base_model: mistralai/Mistral-7B-v0.1
datasets:
- argilla/distilabel-capybara-dpo-7k-binarized
exported_from: alvarobartt/mistral-7b-orpo-capybara-reproduction
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- alignment-handbook
- trl
- orpo
- generated_from_trainer
- trl
- orpo
- generated_from_trainer
---
## About
static quants of https://huggingface.co/alvarobartt/mistral-7b-orpo-capybara-reproduction
<!-- 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/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.IQ3_M.gguf) | IQ3_M | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-capybara-reproduction-GGUF/resolve/main/mistral-7b-orpo-capybara-reproduction.Q8_0.gguf) | Q8_0 | 7.9 | 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 -->