From 1d8146570b3ee8ade810bdf9a8d89817850c4eff Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 25 May 2026 19:33:17 +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/Qwen2.5-Math-7B-CFT-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++++++++ Qwen2.5-Math-7B-CFT.i1-IQ1_M.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ1_S.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ2_M.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ2_S.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ2_XS.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ2_XXS.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ3_M.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ3_S.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ3_XS.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ3_XXS.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ4_NL.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-IQ4_XS.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q2_K.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q2_K_S.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q3_K_L.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q3_K_M.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q3_K_S.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q4_0.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q4_1.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q4_K_M.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q4_K_S.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q5_K_M.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q5_K_S.gguf | 3 ++ Qwen2.5-Math-7B-CFT.i1-Q6_K.gguf | 3 ++ README.md | 82 +++++++++++++++++++++++++++++ imatrix.dat | 3 ++ 27 files changed, 217 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ1_M.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ1_S.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ2_M.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ2_S.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ2_XS.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ2_XXS.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ3_M.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ3_S.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ3_XS.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ3_XXS.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ4_NL.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-IQ4_XS.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q2_K.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q2_K_S.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q3_K_L.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q3_K_M.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q3_K_S.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q4_0.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q4_1.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q4_K_M.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q4_K_S.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q5_K_M.gguf create mode 100644 Qwen2.5-Math-7B-CFT.i1-Q5_K_S.gguf create mode 100644 Qwen2.5-Math-7B-CFT.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..837b4a6 --- /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 +Qwen2.5-Math-7B-CFT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-7B-CFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ1_M.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ1_M.gguf new file mode 100644 index 0000000..68cbbee --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8059b7d19a03708803807d897c8111f6987702b3aaa773c129a305671235d1d3 +size 2042197248 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ1_S.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ1_S.gguf new file mode 100644 index 0000000..27307c3 --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed98ee865c1df4259f6ec1b0a8c504add6bf9fdc6fddd5bb777566ca17fc1a3 +size 1903668480 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ2_M.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ2_M.gguf new file mode 100644 index 0000000..30af42f --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aac5dc1d61f940b27ea4380b3d776f40c48095a632cf66655e0fc2b1fa67476 +size 2780343552 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ2_S.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ2_S.gguf new file mode 100644 index 0000000..9f76913 --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7cf061d9831d8ba35782d4965235f30eb3205f46593de4cb7264b03d54482bf +size 2595638528 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ2_XS.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4f53f25 --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bb284c20600fbcff151044a6a461c6dbd5a0bad6a67026f946a188c5724cac5 +size 2469022976 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ2_XXS.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c126405 --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69352bb5a22a2a4b38f8ec487ec3987f004b8a42bbce97c4573f6a97e419a88e +size 2273078528 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ3_M.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ3_M.gguf new file mode 100644 index 0000000..33a32be --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f482ca136f403c09f293e5b47711327a53098f43af9534a571fbaf2ffab7e9dd +size 3574013184 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ3_S.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ3_S.gguf new file mode 100644 index 0000000..5139fc4 --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2991806c51c42fb18967ea645b230b5eb5f8331790a1e23e899a61316aea6404 +size 3499193600 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ3_XS.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..1c31035 --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a75c17067defb4d02f8ef63fcf537ffe572d0ee5bd3823027939c65a6df5cc +size 3346257152 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ3_XXS.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..6a7eb8d --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a04abc503339a4955b0c3103c01e1ff2c88dfef995c9594acef2ab5a97117b3 +size 3114515712 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ4_NL.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ4_NL.gguf new file mode 100644 index 0000000..92e0b5e --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:693c0f50403a9085242517c931e5b7245755e1d15384e47fc35cf2aa6f86a7fd +size 4437814528 diff --git a/Qwen2.5-Math-7B-CFT.i1-IQ4_XS.gguf b/Qwen2.5-Math-7B-CFT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..421747e --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:040b504dd6762e4741a870d1992d99232acb28c81573caf91f065871f59d4641 +size 4218473728 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q2_K.gguf b/Qwen2.5-Math-7B-CFT.i1-Q2_K.gguf new file mode 100644 index 0000000..3df0b54 --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ecc2e9ebd7b1eacbc941263448423697a5bac5dcd09fcf2d558598a125e653a +size 3015941376 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q2_K_S.gguf b/Qwen2.5-Math-7B-CFT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..088b0de --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f771497466a3ad8bfb0f933075c1e3c2e607285709887862ed83f1719d5e2f87 +size 2834074880 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q3_K_L.gguf b/Qwen2.5-Math-7B-CFT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e7abadc --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0354b21fbd721d4ef6e6db76f37a92e59d4c45ce28914adba3c0dda3d6a1492d +size 4088460544 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q3_K_M.gguf b/Qwen2.5-Math-7B-CFT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..aaf3a92 --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d7a6746ac956028beb480ad4ab21f1c198d999bf724694aa384c5a781d2c668 +size 3808392448 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q3_K_S.gguf b/Qwen2.5-Math-7B-CFT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6aa36f1 --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9133a8093b1a23df12d878f45419b3dfc3ab1d4dbab54207284f49806274b645 +size 3492369664 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q4_0.gguf b/Qwen2.5-Math-7B-CFT.i1-Q4_0.gguf new file mode 100644 index 0000000..8af595c --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4532d8c2923f63a8cbb15613cd972149e649150f65c57cea575eac14f41392 +size 4444122368 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q4_1.gguf b/Qwen2.5-Math-7B-CFT.i1-Q4_1.gguf new file mode 100644 index 0000000..251a4af --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:755079242ddeb7a0e7e075a4235a921b303cc4932934c9c98fe64e97dd0c08b0 +size 4873284864 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q4_K_M.gguf b/Qwen2.5-Math-7B-CFT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..450a36d --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f26349d568902620840a55d02b8d00dec07459d6eb1f71ab9550bc675323cfe8 +size 4683074816 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q4_K_S.gguf b/Qwen2.5-Math-7B-CFT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ea6482f --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75ceecde7c2a46aede8615e19f71fc05c1ab6739b00693347bda30d9c072aaf4 +size 4457770240 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q5_K_M.gguf b/Qwen2.5-Math-7B-CFT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..e7ded64 --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c25a1eca25d636920556dd1541a00e23ad9fed91f007f3b9ae09c8a3ca62bb +size 5444832512 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q5_K_S.gguf b/Qwen2.5-Math-7B-CFT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3e7329a --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe5a2dc8b094a6e0a61784f760a09d38b605f2e0475c63f390fe1147f98d313 +size 5315177728 diff --git a/Qwen2.5-Math-7B-CFT.i1-Q6_K.gguf b/Qwen2.5-Math-7B-CFT.i1-Q6_K.gguf new file mode 100644 index 0000000..475f7ed --- /dev/null +++ b/Qwen2.5-Math-7B-CFT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358c28b3b5485fd03a274ec1778502d6faece78b60dc97b513ca17d862f10179 +size 6254200064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d519772 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: TIGER-Lab/Qwen2.5-Math-7B-CFT +datasets: +- TIGER-Lab/WebInstruct-CFT +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- cft +- math +- reasoning +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/TIGER-Lab/Qwen2.5-Math-7B-CFT + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-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/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-7B-CFT-i1-GGUF/resolve/main/Qwen2.5-Math-7B-CFT.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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..73680d1 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f11a20955996f4c8000e017f712c0504e1e3e9dbe7af0a265ef5a07df12c76 +size 4536665