From d45ba635aae88bf7f752e14be5f3f3c7f8dcbb86 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 17 May 2026 14:39:46 +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-MPOA-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++ Llama-3.3-8B-Instruct-MPOA.i1-IQ1_M.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ1_S.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ2_M.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ2_S.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XS.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XXS.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ3_M.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ3_S.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XS.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XXS.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ4_NL.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-IQ4_XS.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q2_K.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q2_K_S.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_L.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_M.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_S.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q4_0.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q4_1.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_M.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_S.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_M.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_S.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.i1-Q6_K.gguf | 3 + Llama-3.3-8B-Instruct-MPOA.imatrix.gguf | 3 + README.md | 85 ++++++++++++++++++++++ 27 files changed, 220 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ1_M.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ1_S.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ2_M.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ2_S.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XS.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XXS.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ3_M.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ3_S.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XS.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XXS.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ4_NL.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-IQ4_XS.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q2_K.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q2_K_S.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_L.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_M.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_S.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q4_0.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q4_1.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_M.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_S.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_M.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_S.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.i1-Q6_K.gguf create mode 100644 Llama-3.3-8B-Instruct-MPOA.imatrix.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..00c68b7 --- /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-MPOA.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ1_M.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ1_M.gguf new file mode 100644 index 0000000..b8a1c54 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5225aa5c71870dec951f25098a4bbddc053d02ce8e009bb23fe2dcc96e94bcde +size 2161977568 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ1_S.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ1_S.gguf new file mode 100644 index 0000000..fbf8e3a --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7a145b61e78dc2b3f91c6261ecaf8552360fe842dcb5cde68fe27046cdeb0ef +size 2019633376 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_M.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_M.gguf new file mode 100644 index 0000000..1be4d7f --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e7799a063e7247d7daafae9792b8358b9317f7f785c1fd5066da3b075bce954 +size 2948286688 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_S.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_S.gguf new file mode 100644 index 0000000..bbd61d3 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1349957465b1ee68608c7e7637976bfae77561e83b0c9fc57abbb13e0a2d813d +size 2758494432 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XS.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XS.gguf new file mode 100644 index 0000000..db9c109 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53cac300f9fc23296c689e2eb80ddc16761a3e14a8bffc0fdc24c002214c911e +size 2605787360 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XXS.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..7083b84 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:227d125545ef0732130f0ae8ab0969b11967c894e6be6c48f0d2f7b7bcbb86c5 +size 2399217888 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_M.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_M.gguf new file mode 100644 index 0000000..eaf7727 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:428f99b6b71bdc8deb4c750e01991a5eced7b38d5e43f708b184c1e337e20cff +size 3784829152 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_S.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_S.gguf new file mode 100644 index 0000000..97980a7 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:822e0efb836627b812ba35f779c92f7d9498b0f2dcfca4b6b902df87bd1517d8 +size 3682330848 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XS.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e5ab94d --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc871fa1b7ccd93cf3e586609a885036f5770df0a655834bf8a3e7a8e0fa2587 +size 3518752992 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XXS.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9130582 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e18b50ca77634445e85821f942a91515f606390bc6c6421e9e9f85adc1b8c8e +size 3274918112 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ4_NL.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f956e6a --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3e3cee33399b6d01881084fe39d8cc74255dc3984b0cdfb9a375cbc92bc456c +size 4677994720 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-IQ4_XS.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-IQ4_XS.gguf new file mode 100644 index 0000000..987f750 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fefe2adeeb2d92065525ef9001d28fd5cdb4e7fc7d1a48e47d223322211a80aa +size 4447668448 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q2_K.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q2_K.gguf new file mode 100644 index 0000000..04f195c --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e86270c90b7e0cd4f452f47daea79650261b5bc59e4b68c95e5835e1d4ba2d03 +size 3179137248 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q2_K_S.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q2_K_S.gguf new file mode 100644 index 0000000..5a751c9 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d062809ad85913db0720f02b01bb2d4290df49d2639bf52293c80e3d79ec0966 +size 2988820704 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_L.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ebb6e05 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8eba0311b1585ed4b02d0b0346a60706cb8b24e7a4ea4e26a84b9538d262e4c +size 4321962208 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_M.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_M.gguf new file mode 100644 index 0000000..5d5430b --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeffc21257e794de9368b88eefdabe974d65361c58a8db657f54fd24ced41401 +size 4018923744 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_S.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_S.gguf new file mode 100644 index 0000000..8e1a88d --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d28e47ee6faca2530757d7d1e01ade2b6776201b5dcf1a3cb52501d0b70e2e6f +size 3664505056 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q4_0.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q4_0.gguf new file mode 100644 index 0000000..b01f028 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6cf494a45140b7280e1f2672dd99b231f0951a4b0105b072850c4e80417cbeb +size 4675897568 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q4_1.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q4_1.gguf new file mode 100644 index 0000000..d3faab5 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967479bb27eb29080bfb8c5f3af1ab22b240bfb4d347549372a696960078e72c +size 5130258656 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_M.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c0821b7 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323c3abb3bae2b8ee2d42de765bd60f4c3c3cddd891810e941ea94586657afee +size 4920740064 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_S.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c0914b9 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5d54c66ff9e3b4d7c375529fc62c8ef661732bc52dd4306900931c27f480b85 +size 4692674784 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_M.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_M.gguf new file mode 100644 index 0000000..47bd86e --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e03bfeffff982258274f74cdfb52e226283cdfe771f1f9b3699a03b6047a5d +size 5732993248 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_S.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_S.gguf new file mode 100644 index 0000000..63e301b --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfbdac1764c055041f723da5dfa171ddfe6550ebf341fd2d1e3b67c6ec974128 +size 5599299808 diff --git a/Llama-3.3-8B-Instruct-MPOA.i1-Q6_K.gguf b/Llama-3.3-8B-Instruct-MPOA.i1-Q6_K.gguf new file mode 100644 index 0000000..baa2d19 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e981e8a2ad427220d426fd885800ed40a369a806ef1ea7e7ba270ac3d9e48a +size 6596012256 diff --git a/Llama-3.3-8B-Instruct-MPOA.imatrix.gguf b/Llama-3.3-8B-Instruct-MPOA.imatrix.gguf new file mode 100644 index 0000000..56b29b3 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83eebb020afb51e81ef718aa2f1bd20bf3b5818931d75a8c729506996dc1e7fe +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2293974 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: YanLabs/Llama-3.3-8B-Instruct-MPOA +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/YanLabs/Llama-3.3-8B-Instruct-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-MPOA-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-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-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-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-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-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-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-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-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-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-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-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-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-i1-GGUF/resolve/main/Llama-3.3-8B-Instruct-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. + +