commit 0d4a46fb588205ae024b2c2dfdcf5f3f79fce86a Author: ModelHub XC Date: Thu Jun 18 14:02:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/magnum-12b-v2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c86ab9e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +magnum-12b-v2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..543d163 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: anthracite-org/magnum-v2-12b +language: +- en +- fr +- de +- es +- it +- pt +- ru +- zh +- ja +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/anthracite-org/magnum-v2-12b + + +static quants are available at https://huggingface.co/mradermacher/magnum-12b-v2-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/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/magnum-12b-v2-i1-GGUF/resolve/main/magnum-12b-v2.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..ab74c6d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08e3c4d21cca01a217be38acb6e04c47272a7594ed64b235f422cdfa271296d +size 7054405 diff --git a/magnum-12b-v2.i1-IQ1_M.gguf b/magnum-12b-v2.i1-IQ1_M.gguf new file mode 100644 index 0000000..d56a961 --- /dev/null +++ b/magnum-12b-v2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25e6d12e86c838ef1c9074bedd03d3ab4ae01e41ff1cdce7f3f47308a821cfd2 +size 3221624480 diff --git a/magnum-12b-v2.i1-IQ1_S.gguf b/magnum-12b-v2.i1-IQ1_S.gguf new file mode 100644 index 0000000..c6ec899 --- /dev/null +++ b/magnum-12b-v2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2037b2b08090113fe0b047999f61e18df475b53d8b9650ad121684e0763db88f +size 2999211680 diff --git a/magnum-12b-v2.i1-IQ2_M.gguf b/magnum-12b-v2.i1-IQ2_M.gguf new file mode 100644 index 0000000..8db4218 --- /dev/null +++ b/magnum-12b-v2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61135265e4696d8600ceaec293f9d93697aa450ef7b286a3b3dc9e80280fe67 +size 4435023520 diff --git a/magnum-12b-v2.i1-IQ2_S.gguf b/magnum-12b-v2.i1-IQ2_S.gguf new file mode 100644 index 0000000..6c2bb57 --- /dev/null +++ b/magnum-12b-v2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09942f661acdd4a26833b6169003e0e186d078d31f8526a8f4ef5e62e89c4b0 +size 4138473120 diff --git a/magnum-12b-v2.i1-IQ2_XS.gguf b/magnum-12b-v2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..aac063e --- /dev/null +++ b/magnum-12b-v2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38209396a64424d7a71a5d2ed850d7581f92049d64cb04958cc1796e40c5d52c +size 3915077280 diff --git a/magnum-12b-v2.i1-IQ2_XXS.gguf b/magnum-12b-v2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..14ceb35 --- /dev/null +++ b/magnum-12b-v2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3591253a41aee3e21628fe6156250e04f5507c8a7e8d4c85512d7817d80be278 +size 3592312480 diff --git a/magnum-12b-v2.i1-IQ3_M.gguf b/magnum-12b-v2.i1-IQ3_M.gguf new file mode 100644 index 0000000..5016bf2 --- /dev/null +++ b/magnum-12b-v2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c43a1a209c9032c953fb2ae91f8cea54bbe3cce5da62c4d1e32fd606900a56c0 +size 5722232480 diff --git a/magnum-12b-v2.i1-IQ3_S.gguf b/magnum-12b-v2.i1-IQ3_S.gguf new file mode 100644 index 0000000..0ef5de0 --- /dev/null +++ b/magnum-12b-v2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7670f0fd89705f6875d5c8ae5fea79b3958856b6e66f80a1907c6a5d6dbd9fa +size 5562078880 diff --git a/magnum-12b-v2.i1-IQ3_XS.gguf b/magnum-12b-v2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f460c05 --- /dev/null +++ b/magnum-12b-v2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5eb46755960ca9eb0f65bb2bddcec1f79910c857a3b3ffa418b4019d19a973 +size 5306488480 diff --git a/magnum-12b-v2.i1-IQ3_XXS.gguf b/magnum-12b-v2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..efa4c32 --- /dev/null +++ b/magnum-12b-v2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14023fcff48478034d890843db69453b0ab9531385a0235f35f64122a183ad9e +size 4945385120 diff --git a/magnum-12b-v2.i1-IQ4_XS.gguf b/magnum-12b-v2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b79c8fd --- /dev/null +++ b/magnum-12b-v2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f5157264a55656e11c52800e1095ec672fe0672a54c0eb3ec635960ee8820d3 +size 6742709920 diff --git a/magnum-12b-v2.i1-Q2_K.gguf b/magnum-12b-v2.i1-Q2_K.gguf new file mode 100644 index 0000000..231b56d --- /dev/null +++ b/magnum-12b-v2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59504c6ef75d8bd359d7f69ea64ba2ffbe4ec075fba62d5f76b449c80f80a787 +size 4791047840 diff --git a/magnum-12b-v2.i1-Q3_K_L.gguf b/magnum-12b-v2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..6ad76ab --- /dev/null +++ b/magnum-12b-v2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ab68073ab2d3ac21f600fa78c0270bb597ee0af5b0ef92458c5d5cdecf9bba +size 6561502880 diff --git a/magnum-12b-v2.i1-Q3_K_M.gguf b/magnum-12b-v2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..883ba51 --- /dev/null +++ b/magnum-12b-v2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:351ab7ac79d020a6f435532a0dbf0a223fe5a11f2e933623c2cd42232564a295 +size 6083090080 diff --git a/magnum-12b-v2.i1-Q3_K_S.gguf b/magnum-12b-v2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f4a016a --- /dev/null +++ b/magnum-12b-v2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d47738cccea535e626557f6cf90be77980bc72c910e2d85e7ecf1f08cc32e6da +size 5534226080 diff --git a/magnum-12b-v2.i1-Q4_0.gguf b/magnum-12b-v2.i1-Q4_0.gguf new file mode 100644 index 0000000..7c8972e --- /dev/null +++ b/magnum-12b-v2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:934730328efd4520d1e12d58c4841e1704ee154d2381449347592ede959fb5f0 +size 7094638240 diff --git a/magnum-12b-v2.i1-Q4_K_M.gguf b/magnum-12b-v2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..772f3e2 --- /dev/null +++ b/magnum-12b-v2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1e2b688bdb04545fe5fdc91619bfd3a07fa1460a28814ed2af92b6048fc6f11 +size 7477204640 diff --git a/magnum-12b-v2.i1-Q4_K_S.gguf b/magnum-12b-v2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..efe98e6 --- /dev/null +++ b/magnum-12b-v2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8654a4973675e0521d567d3ab50c3907cbb7c7ced2f1eccdad36698e4f6faa29 +size 7120197280 diff --git a/magnum-12b-v2.i1-Q5_K_M.gguf b/magnum-12b-v2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..e56da2d --- /dev/null +++ b/magnum-12b-v2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380d7b86eefce211d617ba89f9015c18d2820542a1f7f53b5ae02cd981b17192 +size 8727631520 diff --git a/magnum-12b-v2.i1-Q5_K_S.gguf b/magnum-12b-v2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a41f0d6 --- /dev/null +++ b/magnum-12b-v2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e780aae906a683e3eb02470190ecb8621ad8bc5d5fc2b8b4d47d2be1a7b40c5 +size 8518735520 diff --git a/magnum-12b-v2.i1-Q6_K.gguf b/magnum-12b-v2.i1-Q6_K.gguf new file mode 100644 index 0000000..1130637 --- /dev/null +++ b/magnum-12b-v2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e63e74ce489f8cb28b5e610b984757daf205faa6deab700a53eb8e946fe175d +size 10056210080