commit 0a0168a668fc76f57518bbd03ca8c69e27eab51e Author: ModelHub XC Date: Mon May 18 16:03:10 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/MN-Halide-12b-v1.0-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..08525ec --- /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-Halide-12b-v1.0.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +MN-Halide-12b-v1.0.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MN-Halide-12b-v1.0.i1-IQ1_M.gguf b/MN-Halide-12b-v1.0.i1-IQ1_M.gguf new file mode 100644 index 0000000..13dc5b3 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22a06078d9a2e0095b572fada5348e501ab8fa6c146389a1a0c94d103c0e7c67 +size 3221628800 diff --git a/MN-Halide-12b-v1.0.i1-IQ1_S.gguf b/MN-Halide-12b-v1.0.i1-IQ1_S.gguf new file mode 100644 index 0000000..42156d2 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d2a99dd8f5122d80dc218d9c06877946b2d2fc571393f3e9061d3acbbb2e0d +size 2999216000 diff --git a/MN-Halide-12b-v1.0.i1-IQ2_M.gguf b/MN-Halide-12b-v1.0.i1-IQ2_M.gguf new file mode 100644 index 0000000..09c3981 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3835bef920c9dd23ac8cdd54259ee1d31045fb0163d23570b0af839ebf1ebc5c +size 4435027840 diff --git a/MN-Halide-12b-v1.0.i1-IQ2_S.gguf b/MN-Halide-12b-v1.0.i1-IQ2_S.gguf new file mode 100644 index 0000000..caf023a --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96a007a666ebeb1e41a17852ad3790af4666517d4ac07ee85aeb49184a60cfd3 +size 4138477440 diff --git a/MN-Halide-12b-v1.0.i1-IQ2_XS.gguf b/MN-Halide-12b-v1.0.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b426649 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dab04751778430fcc70d24d1531aed357cd9dd775d18c4b80dc1c5a3b096d930 +size 3915081600 diff --git a/MN-Halide-12b-v1.0.i1-IQ2_XXS.gguf b/MN-Halide-12b-v1.0.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c339e33 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:787f3c0a592fa26f61ef7d2a7ba314a9dd9cf83d8f4407d4949091c3eb81a9bb +size 3592316800 diff --git a/MN-Halide-12b-v1.0.i1-IQ3_M.gguf b/MN-Halide-12b-v1.0.i1-IQ3_M.gguf new file mode 100644 index 0000000..ba33bea --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b650dbcaa8262468ec932043ae4366dd03d3802e28beffe21363f0a727a72af3 +size 5722236800 diff --git a/MN-Halide-12b-v1.0.i1-IQ3_S.gguf b/MN-Halide-12b-v1.0.i1-IQ3_S.gguf new file mode 100644 index 0000000..2498c98 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff6990708b0a9325f52e4cd88577d78b9490ef1170d8aef14e8bef640de9604 +size 5562083200 diff --git a/MN-Halide-12b-v1.0.i1-IQ3_XS.gguf b/MN-Halide-12b-v1.0.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d521461 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bed54214690ca258860de63a24c4ae0234ae21d78092f2b8e48a9d49cc61f7b +size 5306492800 diff --git a/MN-Halide-12b-v1.0.i1-IQ3_XXS.gguf b/MN-Halide-12b-v1.0.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..999a07e --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b519887ea2ee944d75267e26202c48f976f7d039b66eacc53578accc87c16f67 +size 4945389440 diff --git a/MN-Halide-12b-v1.0.i1-IQ4_XS.gguf b/MN-Halide-12b-v1.0.i1-IQ4_XS.gguf new file mode 100644 index 0000000..4d0e401 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773a896309f26efb254f8e052df3ef89583abb469abaf81437da2f2c088e886e +size 6742714240 diff --git a/MN-Halide-12b-v1.0.i1-Q2_K.gguf b/MN-Halide-12b-v1.0.i1-Q2_K.gguf new file mode 100644 index 0000000..e5cd6c6 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8bba72fcac16bc5dd1a95aee0b63d86157d61de7c25a1bd123218946065b505 +size 4791052160 diff --git a/MN-Halide-12b-v1.0.i1-Q3_K_L.gguf b/MN-Halide-12b-v1.0.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1fd9e27 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f58224608a433c6474c08c0543c66cff30f2f3f7089eae9dd8f87c177f40c8 +size 6561507200 diff --git a/MN-Halide-12b-v1.0.i1-Q3_K_M.gguf b/MN-Halide-12b-v1.0.i1-Q3_K_M.gguf new file mode 100644 index 0000000..3a7c737 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bebf964fa6c55be10a07d570ed69839c54cf3852c13f7482a65a7511616fb9f +size 6083094400 diff --git a/MN-Halide-12b-v1.0.i1-Q3_K_S.gguf b/MN-Halide-12b-v1.0.i1-Q3_K_S.gguf new file mode 100644 index 0000000..12b11ae --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67f275ee42d3db28db04fb6ef29c2ec7a4b9392dbd1089f3f31595429489bb21 +size 5534230400 diff --git a/MN-Halide-12b-v1.0.i1-Q4_0.gguf b/MN-Halide-12b-v1.0.i1-Q4_0.gguf new file mode 100644 index 0000000..3b2a05f --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f85d4d5288b4f7b6fa43c63adb23a22924df984bffa57cdb462fb237c206027f +size 7094642560 diff --git a/MN-Halide-12b-v1.0.i1-Q4_0_4_4.gguf b/MN-Halide-12b-v1.0.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..8305d0c --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef123e1524c86f25c9700f68662c44f4c44b488ecd3a16a1c8f918d40e38ea8e +size 7071704960 diff --git a/MN-Halide-12b-v1.0.i1-Q4_0_4_8.gguf b/MN-Halide-12b-v1.0.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..4b4945f --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf5b087196b664f341a588ab337c795a251250ebcaf2964cb3587cd6564cbb1 +size 7071704960 diff --git a/MN-Halide-12b-v1.0.i1-Q4_0_8_8.gguf b/MN-Halide-12b-v1.0.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..955136a --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f27aa7815e47558377c694925cd2fd2b074f72490d59a80f56dcd31501d68d95 +size 7071704960 diff --git a/MN-Halide-12b-v1.0.i1-Q4_K_M.gguf b/MN-Halide-12b-v1.0.i1-Q4_K_M.gguf new file mode 100644 index 0000000..dee1d27 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18d86eb114f35551971c4ed19da328a3942bca21ac70e34eaf56d107b8ecc6a5 +size 7477208960 diff --git a/MN-Halide-12b-v1.0.i1-Q4_K_S.gguf b/MN-Halide-12b-v1.0.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4c2924a --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04006b8ee404f637023cff4140cd43059eccfca645462f0fe32065396d6adc6b +size 7120201600 diff --git a/MN-Halide-12b-v1.0.i1-Q5_K_M.gguf b/MN-Halide-12b-v1.0.i1-Q5_K_M.gguf new file mode 100644 index 0000000..9f34ccd --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d5d115d3055b7d5e9c96041dcfcce5aa64afaeefd036584e529078e97ef7be8 +size 8727635840 diff --git a/MN-Halide-12b-v1.0.i1-Q5_K_S.gguf b/MN-Halide-12b-v1.0.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d2119b1 --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7d65f80227530113cf8b5888a2a0e441f81492f131cededa71ea2d5b0e49ee5 +size 8518739840 diff --git a/MN-Halide-12b-v1.0.i1-Q6_K.gguf b/MN-Halide-12b-v1.0.i1-Q6_K.gguf new file mode 100644 index 0000000..47ab37f --- /dev/null +++ b/MN-Halide-12b-v1.0.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816d19a3eec2ea847ce0b71b2107b570ab3c3d3dcddb38418cfa7fe4450c742d +size 10056214400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..70e6ce1 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Azazelle/MN-Halide-12b-v1.0 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Azazelle/MN-Halide-12b-v1.0 + + +static quants are available at https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-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-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 7.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.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-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.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-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Halide-12b-v1.0-i1-GGUF/resolve/main/MN-Halide-12b-v1.0.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..525ccdc --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d8978a1451d4a4861099ad61ccb1c6019787884b4e8f9d36648cc8da448597 +size 7054405