From b655fae3237140aa515d54e2d8b022da4b358783 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 13 May 2026 13:40:22 +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-EIRAI-8B-Prob-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++++ Llama-3.1-EIRAI-8B-Prob.i1-IQ1_M.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-IQ1_S.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-IQ2_M.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-IQ2_S.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XS.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XXS.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-IQ3_M.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-IQ3_S.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XS.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XXS.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-IQ4_XS.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q2_K.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_L.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_M.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_S.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q4_0.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_4.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_8.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_8_8.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_M.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_S.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_M.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_S.gguf | 3 + Llama-3.1-EIRAI-8B-Prob.i1-Q6_K.gguf | 3 + README.md | 82 ++++++++++++++++++++++++ imatrix.dat | 3 + 27 files changed, 217 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ1_M.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ1_S.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ2_M.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ2_S.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XS.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XXS.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ3_M.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ3_S.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XS.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XXS.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-IQ4_XS.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q2_K.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_L.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_M.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_S.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q4_0.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_4.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_8.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_8_8.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_M.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_S.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_M.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_S.gguf create mode 100644 Llama-3.1-EIRAI-8B-Prob.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..067f5e1 --- /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-EIRAI-8B-Prob.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EIRAI-8B-Prob.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ1_M.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ1_M.gguf new file mode 100644 index 0000000..bd0a3f3 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b07453f82c385a4604a15a6ab273a8f2d4a9a3189efc043af6fd705d55d0c2b +size 2161972960 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ1_S.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ1_S.gguf new file mode 100644 index 0000000..86dac2e --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c8ac3070d0581ca23f1f93f9b1f09c3708c3911bd797d700cdbe4a0eb4fe460 +size 2019628768 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_M.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_M.gguf new file mode 100644 index 0000000..21aaa8c --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:759c45fe4995d8c98f4eb1b56d78509495a94bcf3aad35da1f80d4c6fac28937 +size 2948282080 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_S.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_S.gguf new file mode 100644 index 0000000..86a01ae --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c429924eb87689e737506851bdf4be315dac51d28804372d0f721641101e6af9 +size 2758489824 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XS.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b0f65f1 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2516333f0e193b400a8c5c0a882c5b917c9b7f6abae72094d36f1226f34c6c8a +size 2605782752 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XXS.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..f31decc --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d828210f6fd03ad170f32c076eadc30d76d315fdd3887e74d312d70aad50fa0e +size 2399213280 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_M.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_M.gguf new file mode 100644 index 0000000..63d1ee4 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c449db5af3e7de0e828353548f7cab0cf589be4235b8b340cc32f99ec661db6f +size 3784824544 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_S.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_S.gguf new file mode 100644 index 0000000..afc44d5 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47860398355abeee8486fb4cc9ac2c18dc49a443834f18f435a0c182fb6404ec +size 3682326240 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XS.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XS.gguf new file mode 100644 index 0000000..6f43bf5 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a899f6b983187186d594326e5bd3be1de21a4ecdc4a4e5834bc9cfe5d20e4155 +size 3518748384 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XXS.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..cb59392 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4abae99bc570236a89e55710dceaeff1ab5928f9b5767980ab4680de806e8eb +size 3274913504 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-IQ4_XS.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9978a6a --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98525c3960c02d554a279ee76164d88b0fc6153b6ff71e53d61eafdb79186ce8 +size 4447663840 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q2_K.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q2_K.gguf new file mode 100644 index 0000000..d862848 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12d4091ca8e1c0a63abd83caa31c9cdf7bcd823467639def741b598761921378 +size 3179132640 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_L.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_L.gguf new file mode 100644 index 0000000..118b0c3 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f58092f9dd4353b5914b8749b205200d518f1ad7853a8d80c4c7efecd84654d4 +size 4321957600 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_M.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2759c25 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89116c93a39eab119d77ecfdd7983758532b1c4489a67fafb6c425f6f20e16cd +size 4018919136 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_S.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e127084 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b95f1b1d2b76becba9a11b45a1ccc8d8b76d9bfb45c9417734a27441bb8782 +size 3664500448 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0.gguf new file mode 100644 index 0000000..ca88b2a --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56c8ba6467796a7870081dad638bfc784a4ccd821ac2192a6974e21eaef29691 +size 4675892960 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_4.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..54d08a7 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc639749c350feb38271ea742360b27cd0017857f2f51dffeaf9cf6e554b7c4 +size 4661212896 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_8.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..c3b40d6 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2060d77fa2d3ff39786c70844b3c7ca4ec8eb25c941c7f1337bf95c6727740b7 +size 4661212896 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_8_8.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..8212a1a --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6503e54f532fd832d96d8067f1cf34e9daf07753efaa407dbedfc56f7f2f5fb +size 4661212896 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_M.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_M.gguf new file mode 100644 index 0000000..0c20b0d --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39d7bd5b46694b4441b2c79ad85e303803dce6d81b339772ec554d7019bac7d4 +size 4920735456 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_S.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_S.gguf new file mode 100644 index 0000000..882f430 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0383e99a84fc8e8a377226921819e1c51756e91a1eff418458670a08f6c22f9 +size 4692670176 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_M.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_M.gguf new file mode 100644 index 0000000..0a14158 --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:777e5fc8256bbc368e8df447322f98b2813f32c61d4432fd601ffc91e2844719 +size 5732988640 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_S.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a1fa22b --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82b188d844a1ed680af01cde1a1f6e6fa51f267c04ef56105a71efb74b7cd7f1 +size 5599295200 diff --git a/Llama-3.1-EIRAI-8B-Prob.i1-Q6_K.gguf b/Llama-3.1-EIRAI-8B-Prob.i1-Q6_K.gguf new file mode 100644 index 0000000..d4bd4ad --- /dev/null +++ b/Llama-3.1-EIRAI-8B-Prob.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8bdc3885b25211e32ed3307ab4b97aa573a8556c90bd1f7c0cfbf488fbbebb9 +size 6596007648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..93fd93e --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: EIRTHAIMED/Llama-3.1-EIRAI-8B-Prob +language: +- th +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- medical +- text-generation-inference +- llama-3.1 +- finetuning +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/EIRTHAIMED/Llama-3.1-EIRAI-8B-Prob + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-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-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EIRAI-8B-Prob-i1-GGUF/resolve/main/Llama-3.1-EIRAI-8B-Prob.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..5091bee --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a667931aada3488b5f3b6066391e90e45a35f74282f962c1cdbad496a03575a +size 4988157