|
--- |
|
base_model: theprint/ReWiz-7B |
|
datasets: |
|
- KingNish/reasoning-base-20k |
|
- arcee-ai/EvolKit-20k |
|
- cognitivecomputations/WizardLM_alpaca_evol_instruct_70k_unfiltered |
|
language: |
|
- en |
|
library_name: transformers |
|
license: apache-2.0 |
|
quantized_by: mradermacher |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- mistral |
|
- trl |
|
- sft |
|
- theprint |
|
--- |
|
## About |
|
|
|
<!-- ### quantize_version: 2 --> |
|
<!-- ### output_tensor_quantised: 1 --> |
|
<!-- ### convert_type: hf --> |
|
<!-- ### vocab_type: --> |
|
<!-- ### tags: --> |
|
static quants of https://huggingface.co/theprint/ReWiz-7B |
|
|
|
<!-- provided-files --> |
|
weighted/imatrix quants are available at https://huggingface.co/mradermacher/ReWiz-7B-i1-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/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.Q2_K.gguf) | Q2_K | 2.8 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | |
|
| [GGUF](https://huggingface.co/mradermacher/ReWiz-7B-GGUF/resolve/main/ReWiz-7B.f16.gguf) | f16 | 14.6 | 16 bpw, overkill | |
|
|
|
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 --> |
|
|
