commit 8005b2480dc8c3066c32e15ea163f0ee91394a25 Author: ModelHub XC Date: Mon May 25 12:19:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aura-12B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1fb1ad4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-12B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aura-12B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aura-12B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aura-12B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aura-12B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aura-12B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aura-12B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aura-12B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aura-12B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aura-12B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aura-12B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aura-12B.IQ4_XS.gguf b/Aura-12B.IQ4_XS.gguf new file mode 100644 index 0000000..2a884d0 --- /dev/null +++ b/Aura-12B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e538a41f1e8a3cef90105236cd215c11bed5d73ec1494cabf2e4abee9f91c1a9 +size 6800054016 diff --git a/Aura-12B.Q2_K.gguf b/Aura-12B.Q2_K.gguf new file mode 100644 index 0000000..eeefb64 --- /dev/null +++ b/Aura-12B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b9409f234af12091690914a7ffd0547887d363473a6498791ef525163f43b2 +size 4791047936 diff --git a/Aura-12B.Q3_K_L.gguf b/Aura-12B.Q3_K_L.gguf new file mode 100644 index 0000000..499c0cb --- /dev/null +++ b/Aura-12B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7787a6ad590a39cd414bcbcf07f021295791cbf66565cac3d21e033facab83b8 +size 6561502976 diff --git a/Aura-12B.Q3_K_M.gguf b/Aura-12B.Q3_K_M.gguf new file mode 100644 index 0000000..a92b5fa --- /dev/null +++ b/Aura-12B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52832c20dc410f55ed240a598ff5ef37bedb4cd704f3ebbac234fe270cae7b63 +size 6083090176 diff --git a/Aura-12B.Q3_K_S.gguf b/Aura-12B.Q3_K_S.gguf new file mode 100644 index 0000000..9f20965 --- /dev/null +++ b/Aura-12B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f084bdfc2ef19fdd95080f803f09ae0e7911552e3cbe17486de5dba9dccd47f +size 5534226176 diff --git a/Aura-12B.Q4_K_M.gguf b/Aura-12B.Q4_K_M.gguf new file mode 100644 index 0000000..67c8d10 --- /dev/null +++ b/Aura-12B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:807704c085352bd495acfcb9c404177f5272ad8e0271e647d0166d17c26a1fc2 +size 7477204736 diff --git a/Aura-12B.Q4_K_S.gguf b/Aura-12B.Q4_K_S.gguf new file mode 100644 index 0000000..031d4f1 --- /dev/null +++ b/Aura-12B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe85a19f574ab6301e3658f2b4cc75f23754eaf3c25ff3d888477d0c56d9769 +size 7120197376 diff --git a/Aura-12B.Q5_K_M.gguf b/Aura-12B.Q5_K_M.gguf new file mode 100644 index 0000000..3edb8c3 --- /dev/null +++ b/Aura-12B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5235659652227aeb8fc0cfbd8574a4cf2a7c230201663241316ba52164a5fd9 +size 8727631616 diff --git a/Aura-12B.Q5_K_S.gguf b/Aura-12B.Q5_K_S.gguf new file mode 100644 index 0000000..6813e56 --- /dev/null +++ b/Aura-12B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4270c41f72c54cac11c6effccb6bf34ea97821248c307c28b16bdae7de31b11 +size 8518735616 diff --git a/Aura-12B.Q6_K.gguf b/Aura-12B.Q6_K.gguf new file mode 100644 index 0000000..f931a11 --- /dev/null +++ b/Aura-12B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f3d8d2ac82f5f7caa75b27ab26c3886d69233c05fac9a884c12613b822262c6 +size 10056210176 diff --git a/Aura-12B.Q8_0.gguf b/Aura-12B.Q8_0.gguf new file mode 100644 index 0000000..b35f4d6 --- /dev/null +++ b/Aura-12B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c167d681b750462ab86616f19e6c182da599d27936e1b00f4a53ccdb1eb133a6 +size 13022369536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2079dc8 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: hardlyworking/Aura-12B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/hardlyworking/Aura-12B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Aura-12B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Aura-12B-i1-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/Aura-12B-GGUF/resolve/main/Aura-12B.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-12B-GGUF/resolve/main/Aura-12B.Q3_K_S.gguf) | Q3_K_S | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-12B-GGUF/resolve/main/Aura-12B.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aura-12B-GGUF/resolve/main/Aura-12B.Q3_K_L.gguf) | Q3_K_L | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-12B-GGUF/resolve/main/Aura-12B.IQ4_XS.gguf) | IQ4_XS | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-12B-GGUF/resolve/main/Aura-12B.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aura-12B-GGUF/resolve/main/Aura-12B.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aura-12B-GGUF/resolve/main/Aura-12B.Q5_K_S.gguf) | Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-12B-GGUF/resolve/main/Aura-12B.Q5_K_M.gguf) | Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/Aura-12B-GGUF/resolve/main/Aura-12B.Q6_K.gguf) | Q6_K | 10.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aura-12B-GGUF/resolve/main/Aura-12B.Q8_0.gguf) | Q8_0 | 13.1 | fast, best quality | + +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. + +