diff --git a/README.md b/README.md index fb9aaa0..17ba5b6 100644 --- a/README.md +++ b/README.md @@ -20,74 +20,6 @@ tags: --- ## About - - - - - -weighted/imatrix quants of https://huggingface.co/drwlf/Medra4b-abliterated - - - -***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Medra4b-abliterated-i1-GGUF).*** - -static quants are available at https://huggingface.co/mradermacher/Medra4b-abliterated-GGUF - -**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Medra4b-abliterated-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/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ1_S.gguf) | i1-IQ1_S | 1.5 | for the desperate | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ1_M.gguf) | i1-IQ1_M | 1.5 | mostly desperate | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.6 | | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.7 | | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ2_S.gguf) | i1-IQ2_S | 1.8 | | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ2_M.gguf) | i1-IQ2_M | 1.9 | | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.0 | very low quality | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q2_K.gguf) | i1-Q2_K | 2.0 | IQ3_XXS probably better | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.1 | lower quality | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.3 | | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ3_S.gguf) | i1-IQ3_S | 2.3 | beats Q3_K* | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.3 | IQ3_XS probably better | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ3_M.gguf) | i1-IQ3_M | 2.4 | | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.5 | IQ3_S probably better | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.6 | IQ3_M probably better | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.7 | | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.8 | prefer IQ4_XS | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q4_0.gguf) | i1-Q4_0 | 2.8 | fast, low quality | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.9 | optimal size/speed/quality | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q4_K_M.gguf) | i1-Q4_K_M | 3.0 | fast, recommended | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q4_1.gguf) | i1-Q4_1 | 3.1 | | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.3 | | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.4 | | -| [GGUF](https://huggingface.co/mradermacher/Medra4b-abliterated-i1-GGUF/resolve/main/Medra4b-abliterated.i1-Q6_K.gguf) | i1-Q6_K | 3.8 | practically like static Q6_K | - -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. 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. +Medra4b-abliterated-GGUF BUT with vision.