From 86ed6aa1732e95f1450a42cf1d59bfd672f4aaff Mon Sep 17 00:00:00 2001 From: team mradermacher Date: Wed, 9 Apr 2025 00:34:22 +0000 Subject: [PATCH] auto-patch README.md --- README.md | 69 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) diff --git a/README.md b/README.md index 53679aa..ea90be3 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,75 @@ +--- +base_model: Secbone/llama-33B-instructed +language: +- en +library_name: transformers +license: gpl-3.0 +quantized_by: mradermacher +--- +## About + weighted/imatrix quants of https://huggingface.co/Secbone/llama-33B-instructed + + +static quants are available at https://huggingface.co/mradermacher/llama-33B-instructed-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/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ1_S.gguf) | i1-IQ1_S | 7.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ1_M.gguf) | i1-IQ1_M | 7.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ2_M.gguf) | i1-IQ2_M | 11.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q2_K.gguf) | i1-Q2_K | 12.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ3_S.gguf) | i1-IQ3_S | 14.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ3_M.gguf) | i1-IQ3_M | 15.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q4_0.gguf) | i1-Q4_0 | 18.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q4_1.gguf) | i1-Q4_1 | 20.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.1 | | +| [GGUF](https://huggingface.co/mradermacher/llama-33B-instructed-i1-GGUF/resolve/main/llama-33B-instructed.i1-Q6_K.gguf) | i1-Q6_K | 26.8 | 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. + +