commit 14cdb09bb688eec6acebf2b02822aec9011d2638 Author: ModelHub XC Date: Mon Apr 27 15:53:38 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aura-MoE-2x4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2422642 --- /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 +Aura-MoE-2x4B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aura-MoE-2x4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aura-MoE-2x4B.IQ4_XS.gguf b/Aura-MoE-2x4B.IQ4_XS.gguf new file mode 100644 index 0000000..e613b3c --- /dev/null +++ b/Aura-MoE-2x4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29bd2e18816e1ca0740700dd17f3f60570752ea5b5428c9748c78cdc8042eaa0 +size 4015615808 diff --git a/Aura-MoE-2x4B.Q2_K.gguf b/Aura-MoE-2x4B.Q2_K.gguf new file mode 100644 index 0000000..8bc1987 --- /dev/null +++ b/Aura-MoE-2x4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a37f9749266ce37191332990ba407f84c5c6e720c154972259ff59a7d8ccac +size 2824355648 diff --git a/Aura-MoE-2x4B.Q3_K_L.gguf b/Aura-MoE-2x4B.Q3_K_L.gguf new file mode 100644 index 0000000..0b4b2eb --- /dev/null +++ b/Aura-MoE-2x4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df67d73343a27ba51c5d29b75b09b0d63ce14249e4291006b01326df146c6819 +size 3867072320 diff --git a/Aura-MoE-2x4B.Q3_K_M.gguf b/Aura-MoE-2x4B.Q3_K_M.gguf new file mode 100644 index 0000000..6bbb99c --- /dev/null +++ b/Aura-MoE-2x4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2160efb1f843d458674492c13f6770f08de37d0d330c56ffb3b00a8db3867d +size 3592607552 diff --git a/Aura-MoE-2x4B.Q3_K_S.gguf b/Aura-MoE-2x4B.Q3_K_S.gguf new file mode 100644 index 0000000..4b842b3 --- /dev/null +++ b/Aura-MoE-2x4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5ebfffbb1d654f5cd28e6ca86a5657070069c7dd1146b5c0b154fb811b0431e +size 3270170432 diff --git a/Aura-MoE-2x4B.Q4_K_M.gguf b/Aura-MoE-2x4B.Q4_K_M.gguf new file mode 100644 index 0000000..ef22cd6 --- /dev/null +++ b/Aura-MoE-2x4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06478a22ccad9d7deae77f2ef137c08598ca25fa0c827aba7d505450077ce4a7 +size 4424683328 diff --git a/Aura-MoE-2x4B.Q4_K_S.gguf b/Aura-MoE-2x4B.Q4_K_S.gguf new file mode 100644 index 0000000..90ffb96 --- /dev/null +++ b/Aura-MoE-2x4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14733f7b4db083a7f5182a73173fd4197633b11348ea4ea4ee896c92958cb698 +size 4208021312 diff --git a/Aura-MoE-2x4B.Q5_K_M.gguf b/Aura-MoE-2x4B.Q5_K_M.gguf new file mode 100644 index 0000000..b8756ce --- /dev/null +++ b/Aura-MoE-2x4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c06b1d0fdcbf1db5dc7227d9de0ce535772bae33ebc8badbc6baa5b3fe4c447c +size 5159702336 diff --git a/Aura-MoE-2x4B.Q5_K_S.gguf b/Aura-MoE-2x4B.Q5_K_S.gguf new file mode 100644 index 0000000..258523d --- /dev/null +++ b/Aura-MoE-2x4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32f865fadd36e1b2676d2fdfb4237de89c14ce77e53a9545f24ad1e5cd8b8791 +size 5032693568 diff --git a/Aura-MoE-2x4B.Q6_K.gguf b/Aura-MoE-2x4B.Q6_K.gguf new file mode 100644 index 0000000..f426152 --- /dev/null +++ b/Aura-MoE-2x4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682d189f1cfb543c24fff64d201880d22a7f4d78e46dc2218820fae2ddbd7ccc +size 5940660032 diff --git a/Aura-MoE-2x4B.Q8_0.gguf b/Aura-MoE-2x4B.Q8_0.gguf new file mode 100644 index 0000000..d0f9587 --- /dev/null +++ b/Aura-MoE-2x4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:758e3028bdd24cd131f6748104cf7c2714c78c3e7321b9eb2ef7212a894dd492 +size 7691786048 diff --git a/Aura-MoE-2x4B.f16.gguf b/Aura-MoE-2x4B.f16.gguf new file mode 100644 index 0000000..71d7f57 --- /dev/null +++ b/Aura-MoE-2x4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f786f64409c020c2ef8434d55f62635ebe2e06f08c28705f106a148e677b528d +size 14470338368 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2a721dd --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: AuraIndustries/Aura-MoE-2x4B +datasets: +- Mielikki/Erebus-87k +- FourOhFour/Instruct_Phase +- FourOhFour/RP_Phase +- anthracite-core/full-opus-chosen-hermes-rejected-kto-v1 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/AuraIndustries/Aura-MoE-2x4B + + +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/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.Q2_K.gguf) | Q2_K | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.Q3_K_M.gguf) | Q3_K_M | 3.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.Q3_K_L.gguf) | Q3_K_L | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.IQ4_XS.gguf) | IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.Q5_K_M.gguf) | Q5_K_M | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Aura-MoE-2x4B-GGUF/resolve/main/Aura-MoE-2x4B.f16.gguf) | f16 | 14.6 | 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. + +