commit 85b56deb487dcff53f2dcd9e7535aae7f9372b03 Author: ModelHub XC Date: Tue May 26 05:34:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MacroMedAI-Assistant-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1c7fe59 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MacroMedAI-Assistant.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MacroMedAI-Assistant.IQ4_XS.gguf b/MacroMedAI-Assistant.IQ4_XS.gguf new file mode 100644 index 0000000..d2059ea --- /dev/null +++ b/MacroMedAI-Assistant.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34551e30eff3c58b938718f03c51dbcf34c90d4a61b1d0578adcb7e98eb7ab2b +size 1501217664 diff --git a/MacroMedAI-Assistant.Q2_K.gguf b/MacroMedAI-Assistant.Q2_K.gguf new file mode 100644 index 0000000..896147a --- /dev/null +++ b/MacroMedAI-Assistant.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1287ebe6ca6edcb9a6d1c054dccf9d639406b5574793c2ad5740c56908498bc +size 1157923712 diff --git a/MacroMedAI-Assistant.Q3_K_L.gguf b/MacroMedAI-Assistant.Q3_K_L.gguf new file mode 100644 index 0000000..5467037 --- /dev/null +++ b/MacroMedAI-Assistant.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2f0ab5a8613b0eb481e68563d673452cf32df47edf91899636faf073b19377 +size 1465590656 diff --git a/MacroMedAI-Assistant.Q3_K_M.gguf b/MacroMedAI-Assistant.Q3_K_M.gguf new file mode 100644 index 0000000..9c0fc54 --- /dev/null +++ b/MacroMedAI-Assistant.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a38511cae5e049895f1d180d6325332b819a85e943b9118c837604e1c8cf82c +size 1383801728 diff --git a/MacroMedAI-Assistant.Q3_K_S.gguf b/MacroMedAI-Assistant.Q3_K_S.gguf new file mode 100644 index 0000000..d1afb1c --- /dev/null +++ b/MacroMedAI-Assistant.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87c381c6c17060c11a9c1d5107c531157a5977b54cf9813c64c8a92f7256dd34 +size 1287979904 diff --git a/MacroMedAI-Assistant.Q4_K_M.gguf b/MacroMedAI-Assistant.Q4_K_M.gguf new file mode 100644 index 0000000..9135fb3 --- /dev/null +++ b/MacroMedAI-Assistant.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b16c3562fb0ba274c30127320b1de44918f89ba45e3a182742af57651f03be3 +size 1630262144 diff --git a/MacroMedAI-Assistant.Q4_K_S.gguf b/MacroMedAI-Assistant.Q4_K_S.gguf new file mode 100644 index 0000000..becc327 --- /dev/null +++ b/MacroMedAI-Assistant.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba69a19dfba184a9df3cf0be6beceaf8218d98ea000f7ac7a39d4cba2f22bdc +size 1559839616 diff --git a/MacroMedAI-Assistant.Q5_K_M.gguf b/MacroMedAI-Assistant.Q5_K_M.gguf new file mode 100644 index 0000000..5a61565 --- /dev/null +++ b/MacroMedAI-Assistant.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f17454eabcf8433759fd5faa6cdb53a61d135f64e16d16ea245f5abc21b2c394 +size 1839649664 diff --git a/MacroMedAI-Assistant.Q5_K_S.gguf b/MacroMedAI-Assistant.Q5_K_S.gguf new file mode 100644 index 0000000..4ed5bdd --- /dev/null +++ b/MacroMedAI-Assistant.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e92b79f783c8331d898155669c6353aa9414205e8b1ae355a0f49cd875058dbd +size 1798914944 diff --git a/MacroMedAI-Assistant.Q6_K.gguf b/MacroMedAI-Assistant.Q6_K.gguf new file mode 100644 index 0000000..c610cab --- /dev/null +++ b/MacroMedAI-Assistant.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30305f0317b899799127362d6dc139327b055d38371a5477ed3f72b5f566f70a +size 2062123904 diff --git a/MacroMedAI-Assistant.Q8_0.gguf b/MacroMedAI-Assistant.Q8_0.gguf new file mode 100644 index 0000000..71c4af3 --- /dev/null +++ b/MacroMedAI-Assistant.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c0635bf765d6844e8faa53644671992830ae1a33449bfd0ec011a481e3dd2f5 +size 2669069184 diff --git a/MacroMedAI-Assistant.f16.gguf b/MacroMedAI-Assistant.f16.gguf new file mode 100644 index 0000000..6813e6e --- /dev/null +++ b/MacroMedAI-Assistant.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5393bd91e34833f5e3ef60cb45952e25431ac197dc8a2b377435617f5e8e779 +size 5018534784 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2225b24 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: ahmedembedded/MacroMedAI-Assistant +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/ahmedembedded/MacroMedAI-Assistant + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MacroMedAI-Assistant-GGUF).*** + +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/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MacroMedAI-Assistant-GGUF/resolve/main/MacroMedAI-Assistant.f16.gguf) | f16 | 5.1 | 16 bpw, overkill | + +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. + +