commit b1bf7e8f979c75ad5a8e5b95c41bf333439d512c Author: ModelHub XC Date: Sun Oct 4 07:23:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/MN-12B-Siskin-v0.2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..20eaddc --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +MN-12B-Siskin-v0.2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +MN-12B-Siskin-v0.2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MN-12B-Siskin-v0.2.i1-IQ1_M.gguf b/MN-12B-Siskin-v0.2.i1-IQ1_M.gguf new file mode 100644 index 0000000..50eb9cb --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1053c567ab7627f843ba57dc22a48b8128e377eaf80017002bba73632e98b56e +size 3221629440 diff --git a/MN-12B-Siskin-v0.2.i1-IQ1_S.gguf b/MN-12B-Siskin-v0.2.i1-IQ1_S.gguf new file mode 100644 index 0000000..594e7f7 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438bb690c725e7a7da2cdaafb26eec3d21b4c393980bd1d383d272c459caf600 +size 2999216640 diff --git a/MN-12B-Siskin-v0.2.i1-IQ2_M.gguf b/MN-12B-Siskin-v0.2.i1-IQ2_M.gguf new file mode 100644 index 0000000..ddbb92b --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e8d15f6ba040ed222d959357d5585b998d24fd3a530f0ce7047d42a50bee16d +size 4435028480 diff --git a/MN-12B-Siskin-v0.2.i1-IQ2_S.gguf b/MN-12B-Siskin-v0.2.i1-IQ2_S.gguf new file mode 100644 index 0000000..5b6e345 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a10ff2eae1a2349b548cee83232cd1f1fc532a002d198ed10dd043fc20340ae +size 4138478080 diff --git a/MN-12B-Siskin-v0.2.i1-IQ2_XS.gguf b/MN-12B-Siskin-v0.2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..f62aa8c --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37c775a764779d4acdda6b957cfd7305e9a4b47fabcdc68f50ba840ee56641ed +size 3915082240 diff --git a/MN-12B-Siskin-v0.2.i1-IQ2_XXS.gguf b/MN-12B-Siskin-v0.2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5ab5b27 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3c950dfcad6c73061616c8a0802ab7455819df3ad2f00455ae9b2e9a6f1307 +size 3592317440 diff --git a/MN-12B-Siskin-v0.2.i1-IQ3_M.gguf b/MN-12B-Siskin-v0.2.i1-IQ3_M.gguf new file mode 100644 index 0000000..fc3741d --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:081d39763f4269625423fe66acd483d931639c17bace9f9c0ead32da90a417ab +size 5722237440 diff --git a/MN-12B-Siskin-v0.2.i1-IQ3_S.gguf b/MN-12B-Siskin-v0.2.i1-IQ3_S.gguf new file mode 100644 index 0000000..97b5276 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5038fb4beed35558fd8b61f64be675b8ffe1472f32676349dcb58a3338810c95 +size 5562083840 diff --git a/MN-12B-Siskin-v0.2.i1-IQ3_XS.gguf b/MN-12B-Siskin-v0.2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..9a5416e --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a80537c2a414ca88f2c1bc1cd498c0a4112d40cf9a178b403eb8b7ab33415b +size 5306493440 diff --git a/MN-12B-Siskin-v0.2.i1-IQ3_XXS.gguf b/MN-12B-Siskin-v0.2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f6a917f --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab0da0e16b328110669755ce4d0228271432266b098afc6cc800298d3b4e2f91 +size 4945390080 diff --git a/MN-12B-Siskin-v0.2.i1-IQ4_XS.gguf b/MN-12B-Siskin-v0.2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5654753 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f543963dca56484281bd78cb4bf4365d8fe68f1a7e3affdc2a80a7c32ccfc6 +size 6742714880 diff --git a/MN-12B-Siskin-v0.2.i1-Q2_K.gguf b/MN-12B-Siskin-v0.2.i1-Q2_K.gguf new file mode 100644 index 0000000..efd4031 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e8157a85a066e83e20c316f76e6532ab7c0f1e1806e515b4472edee73453edb +size 4791052800 diff --git a/MN-12B-Siskin-v0.2.i1-Q3_K_L.gguf b/MN-12B-Siskin-v0.2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8cb05a4 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62cba772f1a2e421f096a777ffa3e0573a1bbc55db7b549a6edb862318eb73bc +size 6561507840 diff --git a/MN-12B-Siskin-v0.2.i1-Q3_K_M.gguf b/MN-12B-Siskin-v0.2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1c7f93a --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b319fd8c2c8f8f07b2ccb7a66b0067342fa2cb1a55145bf558f625c12e766523 +size 6083095040 diff --git a/MN-12B-Siskin-v0.2.i1-Q3_K_S.gguf b/MN-12B-Siskin-v0.2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c493316 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b904d3830e5d6c2422044607f0f9cd7f68487bb4cfbde7d7feebc088fa1ce7e9 +size 5534231040 diff --git a/MN-12B-Siskin-v0.2.i1-Q4_0.gguf b/MN-12B-Siskin-v0.2.i1-Q4_0.gguf new file mode 100644 index 0000000..ba1cd96 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd53b7769b27b10dfdd4f5bec3abe7e162bd9350252fb08dd1231b58c551d2d4 +size 7094643200 diff --git a/MN-12B-Siskin-v0.2.i1-Q4_0_4_4.gguf b/MN-12B-Siskin-v0.2.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..232b7e7 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c0a8f508bac740807cb58f9dc56b2e8d3ae85d9742b0370bb9394fcc7fa7735 +size 7071705600 diff --git a/MN-12B-Siskin-v0.2.i1-Q4_0_4_8.gguf b/MN-12B-Siskin-v0.2.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..7dfb52f --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f157a4f606e83b0acbc21a735a65f456e791ff6e41764938822a4e8105f8a1c +size 7071705600 diff --git a/MN-12B-Siskin-v0.2.i1-Q4_0_8_8.gguf b/MN-12B-Siskin-v0.2.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..e782fca --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba19ab9486c99d45041ece71130a2060615456ea4b85bedc1e72be5029ede97 +size 7071705600 diff --git a/MN-12B-Siskin-v0.2.i1-Q4_K_M.gguf b/MN-12B-Siskin-v0.2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..7bea84d --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1260ab72ad9f4438d129434df140c76ac2c9dee2c7c0ec820a092326717941db +size 7477209600 diff --git a/MN-12B-Siskin-v0.2.i1-Q4_K_S.gguf b/MN-12B-Siskin-v0.2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..315b776 --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b8adeb4cb6ef79d0dc85e4fb785bf4bf613b9151dbfc1cf3f9c2fe426a94dc +size 7120202240 diff --git a/MN-12B-Siskin-v0.2.i1-Q5_K_M.gguf b/MN-12B-Siskin-v0.2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..951746d --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84d5cf0163b20b0cc943efd6aa81df592f63e9af0570be31e8b0db9da8c4adc0 +size 8727636480 diff --git a/MN-12B-Siskin-v0.2.i1-Q5_K_S.gguf b/MN-12B-Siskin-v0.2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..0572e4b --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f359b644fa6799cbbe342ab2a506678682482fea9882af3f1110d5ada50dcd6 +size 8518740480 diff --git a/MN-12B-Siskin-v0.2.i1-Q6_K.gguf b/MN-12B-Siskin-v0.2.i1-Q6_K.gguf new file mode 100644 index 0000000..5c1ef8a --- /dev/null +++ b/MN-12B-Siskin-v0.2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66fb31e597f0feb5cf04125c43a2d9aa0e44dc2778f37cec026d0e52cf3136c8 +size 10056215040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..00081fe --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Nohobby/MN-12B-Siskin-v0.2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Nohobby/MN-12B-Siskin-v0.2 + + +static quants are available at https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-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/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 7.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 7.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 7.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/MN-12B-Siskin-v0.2-i1-GGUF/resolve/main/MN-12B-Siskin-v0.2.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..9d49419 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a19b2371df8e2e9d9f34deee503e523201db22bfe643c52850c487895635b1cc +size 7054405