From d69a8a0ae9ab3f4ab65b3c49b926ceb5279d2e61 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 22 Apr 2026 01:39:54 +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-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++ ....3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_M.gguf | 3 + ....3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_S.gguf | 3 + ....3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_M.gguf | 3 + ....3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_S.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XS.gguf | 3 + ...-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XXS.gguf | 3 + ....3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_M.gguf | 3 + ....3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_S.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XS.gguf | 3 + ...-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XXS.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_NL.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_XS.gguf | 3 + ...3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K_S.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_L.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_M.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_S.gguf | 3 + ...3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_0.gguf | 3 + ...3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_1.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_M.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_S.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_M.gguf | 3 + ...3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_S.gguf | 3 + ...3.3-8B-Instruct-128K-SOM-MPOA.i1-Q6_K.gguf | 3 + ...3.3-8B-Instruct-128K-SOM-MPOA.imatrix.gguf | 3 + README.md | 90 +++++++++++++++++++ 27 files changed, 225 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_M.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_S.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_M.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_S.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XS.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XXS.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_M.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_S.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XS.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XXS.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_NL.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_XS.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K_S.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_L.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_M.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_S.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_0.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_1.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_M.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_S.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_M.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_S.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q6_K.gguf create mode 100644 Llama-3.3-8B-Instruct-128K-SOM-MPOA.imatrix.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b6f7168 --- /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 +Llama-3.3-8B-Instruct-128K-SOM-MPOA.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_M.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_M.gguf new file mode 100644 index 0000000..9e25ab3 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c01bb18a179ebf91e0a09e8fabf824a773e21e810e8019d4ca0a25e71bf2330 +size 2161977664 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_S.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_S.gguf new file mode 100644 index 0000000..12d0cae --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f921a9a9867bbae6c6ad209105d910d7adf9f1c502f66c2956c4bf5e9a33713a +size 2019633472 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_M.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_M.gguf new file mode 100644 index 0000000..5d60b93 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4341c147cffcfbe0f77e5cbf302c9ae925f20883e805f140c718009b242bfa0 +size 2948286784 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_S.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_S.gguf new file mode 100644 index 0000000..e62717f --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eba83b010b64af2e70b0598b46aac67578017d7a5cc0bebdfa2b91fcf3128d7 +size 2758494528 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XS.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XS.gguf new file mode 100644 index 0000000..8e32f1d --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd49050329c35f892f25d866bbc0b65ff92a8f82f606b76126fa8c4b749044b +size 2605787456 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XXS.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8f5f8ac --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed7b305d43caaf209e339b7dcc8919013e2bdabef702e2b3eed45e11bcea90d +size 2399217984 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_M.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_M.gguf new file mode 100644 index 0000000..fbe715d --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f1d10e785d88d86c610dfc4efeb1be9fbf45d337cb16c79cd32219b817edcb +size 3784829248 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_S.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_S.gguf new file mode 100644 index 0000000..f05495c --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b3094dbe745807826dfadb5533ac4af4de9a098371810ba52f00e3e5c03a1e6 +size 3682330944 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XS.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XS.gguf new file mode 100644 index 0000000..540295a --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdcd8f6fbab1d169462f2ed49f7ef628b105c2cdb1c3289f1475b3272a9bd15a +size 3518753088 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XXS.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..93987d6 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce8bb6274869eee53c3727416f882e9b5a2a9d2dedb66227ebcb2ab6cdae5443 +size 3274918208 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_NL.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_NL.gguf new file mode 100644 index 0000000..30beaab --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:937c01d5a882d81c7975036f7e4188a5853f3128bffe1125a93d2d7647a58a1c +size 4677994816 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_XS.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_XS.gguf new file mode 100644 index 0000000..99608fa --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abbd1af6fa4a38f4b6e655fb4f3157fb2f79197ad75241ac3ef8650a13a714ac +size 4447668544 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K.gguf new file mode 100644 index 0000000..7b1a3fc --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c4f02a71bb1ef558340a27d42a4560441184c1b0cdb1812ab1e250b72aad02 +size 3179137344 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K_S.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0911aee --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ed6cf5aea0da2a431629fe4f0ab38cd5028f72d28aeaad54c58e7c325d3d728 +size 2988820800 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_L.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_L.gguf new file mode 100644 index 0000000..18cdfca --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ba60efab7c6d932f6bd268de3d7d834e8dfeb599487b4318f65e617522c90e4 +size 4321962304 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_M.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_M.gguf new file mode 100644 index 0000000..49a8c7a --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:117796d7fe199f77cd2f33cff84468da9a5e55009aee316589f9a9b2f1567ba6 +size 4018923840 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_S.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c9881ab --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d11f0e7941d0da986914117b55677be1afc2b9663a3413380d653f1f1a4c92 +size 3664505152 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_0.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_0.gguf new file mode 100644 index 0000000..80f3130 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35feb86efb32fce251000e337f0b0fa0c41f16dbd3ffbe480df60c52de82e09e +size 4675897664 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_1.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_1.gguf new file mode 100644 index 0000000..51486c2 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ec77206500b3e6dcda8c1fb49a5fd5444b35bf994a478156c313f523017fc5 +size 5130258752 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_M.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_M.gguf new file mode 100644 index 0000000..bea10be --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:520f6d2ae96987985d0ff9e10ff4676b7ee9543e1948c3890f9f19fec37fa7a3 +size 4920740160 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_S.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a5ead7b --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b1adff39074765c7a10f1a3cc50cd3aa6ac4a5453044dc365f8dd566dfeedc +size 4692674880 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_M.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_M.gguf new file mode 100644 index 0000000..0ce2d7f --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56dc0acfd162e6015e38fb2a67e6487962149db71c2ebc7f14d86b249af3b8d6 +size 5732993344 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_S.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_S.gguf new file mode 100644 index 0000000..7f8056e --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6b2c0b841f009082dca2821ebf4f5462f5711f05f4cddc24a60d7392e0f78a +size 5599299904 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q6_K.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q6_K.gguf new file mode 100644 index 0000000..1111f5e --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4bc19ad7934bbfc02b800733da96cb3ba20e47786a02f15eaba4e77f10ba7a +size 6596012352 diff --git a/Llama-3.3-8B-Instruct-128K-SOM-MPOA.imatrix.gguf b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.imatrix.gguf new file mode 100644 index 0000000..598b918 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K-SOM-MPOA.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c6b3e0e71312a1c0e0a2b8151568eb6879eadd5242db042603c800f99be8aab +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ac956d2 --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: 0xA50C1A1/Llama-3.3-8B-Instruct-128K-SOM-MPOA +language: +- en +library_name: transformers +license: llama3.3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- heretic +- uncensored +- decensored +- abliterated +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/0xA50C1A1/Llama-3.3-8B-Instruct-128K-SOM-MPOA + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-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-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-SOM-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K-SOM-MPOA.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. + +