From 07746c8624c96acd4bb1d3f61ccee5d03d86c66d Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 5 Jun 2026 05:40:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++++++++ MathCoder2-CodeLlama-7B.i1-IQ1_M.gguf | 3 + MathCoder2-CodeLlama-7B.i1-IQ1_S.gguf | 3 + MathCoder2-CodeLlama-7B.i1-IQ2_M.gguf | 3 + MathCoder2-CodeLlama-7B.i1-IQ2_S.gguf | 3 + MathCoder2-CodeLlama-7B.i1-IQ2_XS.gguf | 3 + MathCoder2-CodeLlama-7B.i1-IQ2_XXS.gguf | 3 + MathCoder2-CodeLlama-7B.i1-IQ3_M.gguf | 3 + MathCoder2-CodeLlama-7B.i1-IQ3_S.gguf | 3 + MathCoder2-CodeLlama-7B.i1-IQ3_XS.gguf | 3 + MathCoder2-CodeLlama-7B.i1-IQ3_XXS.gguf | 3 + MathCoder2-CodeLlama-7B.i1-IQ4_XS.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q2_K.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q3_K_L.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q3_K_M.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q3_K_S.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q4_0.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q4_0_4_4.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q4_0_4_8.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q4_0_8_8.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q4_K_M.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q4_K_S.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q5_K_M.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q5_K_S.gguf | 3 + MathCoder2-CodeLlama-7B.i1-Q6_K.gguf | 3 + README.md | 80 ++++++++++++++++++++++++ imatrix.dat | 3 + 27 files changed, 215 insertions(+) create mode 100644 .gitattributes create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ1_M.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ1_S.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ2_M.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ2_S.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ2_XS.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ2_XXS.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ3_M.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ3_S.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ3_XS.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ3_XXS.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-IQ4_XS.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q2_K.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q3_K_L.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q3_K_M.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q3_K_S.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q4_0.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q4_0_4_4.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q4_0_4_8.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q4_0_8_8.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q4_K_M.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q4_K_S.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q5_K_M.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q5_K_S.gguf create mode 100644 MathCoder2-CodeLlama-7B.i1-Q6_K.gguf create mode 100644 README.md create mode 100644 imatrix.dat diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9af7d18 --- /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 +MathCoder2-CodeLlama-7B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +MathCoder2-CodeLlama-7B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MathCoder2-CodeLlama-7B.i1-IQ1_M.gguf b/MathCoder2-CodeLlama-7B.i1-IQ1_M.gguf new file mode 100644 index 0000000..024a29a --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b7fbf574f99a1c1647a68e99c22c0422159e1812e4fae1c5dc86221546bffe4 +size 1651039104 diff --git a/MathCoder2-CodeLlama-7B.i1-IQ1_S.gguf b/MathCoder2-CodeLlama-7B.i1-IQ1_S.gguf new file mode 100644 index 0000000..2274d32 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9bbe8108d2a204e43a2f5fa56c3745798d719cd002351d4aaa69afd88a89a1 +size 1528650624 diff --git a/MathCoder2-CodeLlama-7B.i1-IQ2_M.gguf b/MathCoder2-CodeLlama-7B.i1-IQ2_M.gguf new file mode 100644 index 0000000..9252fa5 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3240ac3efeeb764858a112f09881375b280b5b99f927b9d65df8e2ea9d27e0b +size 2359825792 diff --git a/MathCoder2-CodeLlama-7B.i1-IQ2_S.gguf b/MathCoder2-CodeLlama-7B.i1-IQ2_S.gguf new file mode 100644 index 0000000..f58cc2a --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f72187dcc2c48d3006baa65a3351b52b5c70a55e82fbec4ddc2a80bb6160fe +size 2196641152 diff --git a/MathCoder2-CodeLlama-7B.i1-IQ2_XS.gguf b/MathCoder2-CodeLlama-7B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2f7b2e0 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12b586f5ed461ad314609cc4a1f398a3651089bfb81b0a84978867bc7054f92a +size 2034981760 diff --git a/MathCoder2-CodeLlama-7B.i1-IQ2_XXS.gguf b/MathCoder2-CodeLlama-7B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8e2ef3e --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e031c075d9e49169c082c0f9144394e07188c2b507573438d62a36a0639193a4 +size 1855019904 diff --git a/MathCoder2-CodeLlama-7B.i1-IQ3_M.gguf b/MathCoder2-CodeLlama-7B.i1-IQ3_M.gguf new file mode 100644 index 0000000..2823cd9 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3add97d8e7c816a0315bf64410e7079cb245e9877a9fdd2945fbfdb928a7716 +size 3114948480 diff --git a/MathCoder2-CodeLlama-7B.i1-IQ3_S.gguf b/MathCoder2-CodeLlama-7B.i1-IQ3_S.gguf new file mode 100644 index 0000000..1d79962 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6240ffacfcc442ff9ea0e0a5507a3c7058e80658397b428121f49ab8d99c77dd +size 2948388736 diff --git a/MathCoder2-CodeLlama-7B.i1-IQ3_XS.gguf b/MathCoder2-CodeLlama-7B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b842902 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc7a6eb3cde811f18d2fa86d38e5f0bec400adc93d8dac2ab0e0d2b593d688e +size 2796607360 diff --git a/MathCoder2-CodeLlama-7B.i1-IQ3_XXS.gguf b/MathCoder2-CodeLlama-7B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c9452f5 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d67e0b7c53f7f97610335d1b2c8b57f48d00489a2b71182b06027a20b5011666 +size 2585466240 diff --git a/MathCoder2-CodeLlama-7B.i1-IQ4_XS.gguf b/MathCoder2-CodeLlama-7B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5ba95be --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d587a848684a7d661d986a52fa6c61cafcd61ca8c5b3ba0aa062f64c8c6e83d1 +size 3619426688 diff --git a/MathCoder2-CodeLlama-7B.i1-Q2_K.gguf b/MathCoder2-CodeLlama-7B.i1-Q2_K.gguf new file mode 100644 index 0000000..69419a7 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63d44683572ab4e411f9efbf2bdeafa3680f0b478c7a06912b705e5eb7c72dc6 +size 2532941184 diff --git a/MathCoder2-CodeLlama-7B.i1-Q3_K_L.gguf b/MathCoder2-CodeLlama-7B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..44aaeb8 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d22619a8cfc3d844db599cbdbe29c815d2c7ed3dab82016fe63db535946de3 +size 3597195136 diff --git a/MathCoder2-CodeLlama-7B.i1-Q3_K_M.gguf b/MathCoder2-CodeLlama-7B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..82a3e54 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3522aca990fdc346c40a25bff2f7bf9a4cdb32753a5c15e38e01dc42e8c54f82 +size 3298088832 diff --git a/MathCoder2-CodeLlama-7B.i1-Q3_K_S.gguf b/MathCoder2-CodeLlama-7B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6be86c2 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3adc76b98b0506e8e47f11af32787ca7ae6e6c3eafd03b4669cca409feb2be11 +size 2948388736 diff --git a/MathCoder2-CodeLlama-7B.i1-Q4_0.gguf b/MathCoder2-CodeLlama-7B.i1-Q4_0.gguf new file mode 100644 index 0000000..f369934 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba07c14cd44b7da933825a0366bb1dc161cfea73385a2196570da0e11816673e +size 3837172096 diff --git a/MathCoder2-CodeLlama-7B.i1-Q4_0_4_4.gguf b/MathCoder2-CodeLlama-7B.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..f6b0cf8 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb404bac5d6ab30200fac4bab6a91ee053b8b63f2fd8c612b1cf38b503b3c05 +size 3825899904 diff --git a/MathCoder2-CodeLlama-7B.i1-Q4_0_4_8.gguf b/MathCoder2-CodeLlama-7B.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..e358817 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1aa1e5fdc8b007c852aa9e82ac967cea6aff3b6a0b74d538e30e576e8b966c8 +size 3825899904 diff --git a/MathCoder2-CodeLlama-7B.i1-Q4_0_8_8.gguf b/MathCoder2-CodeLlama-7B.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..60be449 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4d03c3682d9fadbe20d15b63dd6a80c15b58dabf7e9d41323305a0a35e95dd +size 3825899904 diff --git a/MathCoder2-CodeLlama-7B.i1-Q4_K_M.gguf b/MathCoder2-CodeLlama-7B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..adf1633 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:802730be3b889f851e0613e3294ad0fac71facb167fc5109f9f281ac5f92b341 +size 4081097088 diff --git a/MathCoder2-CodeLlama-7B.i1-Q4_K_S.gguf b/MathCoder2-CodeLlama-7B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..003396a --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a46adde199f0baaec5e188c997ea5a065be57bb33e2355094a28c43c07c626 +size 3856832896 diff --git a/MathCoder2-CodeLlama-7B.i1-Q5_K_M.gguf b/MathCoder2-CodeLlama-7B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4684b98 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af36a59b3c55239e40cb094f7c325ea2e48bb1e9fde47ddcad62ead06715325f +size 4783257984 diff --git a/MathCoder2-CodeLlama-7B.i1-Q5_K_S.gguf b/MathCoder2-CodeLlama-7B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..dbca01b --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c10176649f3eab22857a15a86c98fbf2af87e9b4500f01e5466de6213bbfad +size 4651792768 diff --git a/MathCoder2-CodeLlama-7B.i1-Q6_K.gguf b/MathCoder2-CodeLlama-7B.i1-Q6_K.gguf new file mode 100644 index 0000000..7f235e1 --- /dev/null +++ b/MathCoder2-CodeLlama-7B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4bc794d77da5c6dca6f86d9039961e4aeb3c8b88a22a91b696b5808ea20ecfc +size 5529303936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e7398e5 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: MathGenie/MathCoder2-CodeLlama-7B +datasets: +- MathGenie/MathCode-Pile +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- math +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/MathGenie/MathCoder2-CodeLlama-7B + + +static quants are available at https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-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/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q2_K.gguf) | i1-Q2_K | 2.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 3.9 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 3.9 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q4_0.gguf) | i1-Q4_0 | 3.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/MathCoder2-CodeLlama-7B-i1-GGUF/resolve/main/MathCoder2-CodeLlama-7B.i1-Q6_K.gguf) | i1-Q6_K | 5.6 | 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..4bec6a3 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41d49886bac04bdeab62babd5a0349d002f3f90453928b7020bf4603e04c6ee5 +size 4562173