From 9e1d1b9484786c5cab547c4faf1391fb5113416c Mon Sep 17 00:00:00 2001 From: team mradermacher Date: Tue, 23 Dec 2025 17:58:45 +0000 Subject: [PATCH] auto-patch README.md --- README.md | 80 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) diff --git a/README.md b/README.md index 2c24554..bb7d45d 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,19 @@ +--- +base_model: wowbager/granite-cermat-7b +datasets: +- cermat_all.jsonl +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + @@ -7,3 +23,67 @@ weighted/imatrix quants of https://huggingface.co/wowbager/granite-cermat-7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#granite-cermat-7b-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/granite-cermat-7b-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/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ1_S.gguf) | i1-IQ1_S | 1.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ1_M.gguf) | i1-IQ1_M | 1.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ2_S.gguf) | i1-IQ2_S | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ2_M.gguf) | i1-IQ2_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q2_K.gguf) | i1-Q2_K | 2.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 3.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q4_0.gguf) | i1-Q4_0 | 3.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q4_1.gguf) | i1-Q4_1 | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/granite-cermat-7b-i1-GGUF/resolve/main/granite-cermat-7b.i1-Q6_K.gguf) | i1-Q6_K | 5.6 | 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. + +