From 16d2becc9a9e55a89463394747c17a9a4516347c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 27 Sep 2026 06:01:17 +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/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++ Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_M.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_S.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_M.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_S.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XS.gguf | 3 + ...a-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XXS.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_M.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_S.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XS.gguf | 3 + ...a-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XXS.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_NL.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_XS.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K_S.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_L.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_M.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_S.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_0.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_1.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_M.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_S.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_M.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_S.gguf | 3 + Llama-3.1-8B-Magpie-Align-v0.2.i1-Q6_K.gguf | 3 + README.md | 91 +++++++++++++++++++ imatrix.dat | 3 + 27 files changed, 226 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_M.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_S.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_M.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_S.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XS.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XXS.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_M.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_S.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XS.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XXS.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_NL.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_XS.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K_S.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_L.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_M.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_S.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_0.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_1.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_M.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_S.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_M.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_S.gguf create mode 100644 Llama-3.1-8B-Magpie-Align-v0.2.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..8e51f72 --- /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 +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_M.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_M.gguf new file mode 100644 index 0000000..7b964c4 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3d2a696d918183f39af33164cb72bf10fb27d83bc5adec748edd2bca26fd5c +size 2161973696 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_S.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_S.gguf new file mode 100644 index 0000000..4fa874f --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93978f822118bc094358b77770e24e16d0b0f4fac73c02d8e70515fd2886dcaa +size 2019629504 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_M.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_M.gguf new file mode 100644 index 0000000..ade5b86 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2010b1dde37b392caaa4ccd22877e0dac8742a3f6acc05c36f82b8575aa284b6 +size 2948282816 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_S.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_S.gguf new file mode 100644 index 0000000..6da3ea7 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ebf04c47cd21c0dbc47c06c2e1112ab7606c9c3a10e836986dd47e052337e04 +size 2758490560 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XS.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e8baa55 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e52cdc80152cf22b67c2eb60bcc965fd99a854e05bf0276f0c0325e25b7891de +size 2605783488 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XXS.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4a75e13 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbca14028ffbdd240aba74bbcb7af257497a6fad397f24020e8bde20f4e30758 +size 2399214016 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_M.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_M.gguf new file mode 100644 index 0000000..452d822 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6f596eb98056964d1f51a3a76bb3ed6718b34dc699d20c151c630f5962338c4 +size 3784825280 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_S.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_S.gguf new file mode 100644 index 0000000..92a357b --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad786e5df374f83e10bb1e3716c13e120d481b666c04a663f6ead861ba38b25b +size 3682326976 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XS.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..84dfbd3 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2682faa63c5607fb330c9b90ca09b11106016b07040e2e47efb2f1e31c15275c +size 3518749120 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XXS.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..edfd31a --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e45530069faa705507ae5d25b6bdf237d12ba23a21de03c16af78820955ca57a +size 3274914240 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_NL.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_NL.gguf new file mode 100644 index 0000000..b73156f --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca04f886d105a9778bb0d6d5f5488490e1dcd326951d92abd09e1a17d498e00c +size 4677990848 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_XS.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ba9cf8d --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027dcab16f3e17db2c2cbeb4520684e9beb41f2d4d6a20e251e5fce929ca820d +size 4447664576 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K.gguf new file mode 100644 index 0000000..5c62bcc --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56bedf9a3f9fb5b80839b8984bf51b379c6a70e5ffa4caf28076aa99c9666c8f +size 3179133376 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K_S.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f77459a --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32bda8824e8dd017aae7d8805f132547b8b78be0fdabb204b7f5646f2b214fdd +size 2988816832 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_L.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d111684 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8560217bfe04803f9f21e6673b7b8c5de6a0ba405fa55c6b062462dfc9ef5ad3 +size 4321958336 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_M.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a3df837 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63d30e713b941b8ee48570a790bc1ec40271aba16db65b0daae7ff943f64dea6 +size 4018919872 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_S.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b345fda --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eff27c5068344a72cb7290d868731108fbc239c01f8366e1c37fce90523de369 +size 3664501184 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_0.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_0.gguf new file mode 100644 index 0000000..0c5a972 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6f47ef1fa8a28c0abdba06b124573bece04f0e5f7ba2b9ba6edbbd585eedc95 +size 4675893696 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_1.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_1.gguf new file mode 100644 index 0000000..da2e823 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea35ebbfed573d8557ca643dfdeb1d393c16a9e887514549aed9ed2e46d33fd +size 5130254784 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_M.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c4d9502 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c92cf9f79a3efc1f6d90c3bb23b79c558b2676069bad8ca08951729c223711 +size 4920736192 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_S.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b79350b --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37b0fc383e2f0ee2c801a688c2f3960c56c31fc216929fb10cb53ca0fd43a2e0 +size 4692670912 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_M.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..1c970ba --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90242a83f05e801fb2dd62ef7e488cfbbb054d681ca51a9c25ee0099e3af7f6 +size 5732989376 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_S.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..0b95663 --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc9d1bea9cd71bf6e8102c9117d75c9c1e1c333841bd52f405393a022c73b2f +size 5599295936 diff --git a/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q6_K.gguf b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q6_K.gguf new file mode 100644 index 0000000..cd4701f --- /dev/null +++ b/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d2fd459518538a089ca2e9dd344a1e229b3bbfde523c0005a3e9d122d215dad +size 6596008384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7218b6c --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: Magpie-Align/Llama-3.1-8B-Magpie-Align-v0.2 +datasets: +- Magpie-Align/Llama-3.1-70B-PO-100K-armorm +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- alignment-handbook +- trl +- dpo +- generated_from_trainer +- trl +- dpo +- generated_from_trainer +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Magpie-Align/Llama-3.1-8B-Magpie-Align-v0.2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-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/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-Align-v0.2-i1-GGUF/resolve/main/Llama-3.1-8B-Magpie-Align-v0.2.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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..9afbcaf --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a2bf79439e3eb4881a8d58de8a6ea7bd01f47f41e7749a28c4b5ad1ccb76b0 +size 4988157