From 975a514583f800d1b24ee587e92a5fdced0a811f Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 18 May 2026 08:44:09 +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-Instruct-Uz-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++ Llama-3.1-8B-Instruct-Uz.i1-IQ1_M.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ1_S.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ2_M.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ2_S.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ2_XS.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ2_XXS.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ3_M.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ3_S.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ3_XS.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ3_XXS.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ4_NL.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-IQ4_XS.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q2_K.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q2_K_S.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q3_K_L.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q3_K_M.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q3_K_S.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q4_0.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q4_1.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q4_K_M.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q4_K_S.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q5_K_M.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q5_K_S.gguf | 3 + Llama-3.1-8B-Instruct-Uz.i1-Q6_K.gguf | 3 + Llama-3.1-8B-Instruct-Uz.imatrix.gguf | 3 + README.md | 96 ++++++++++++++++++++++++ 27 files changed, 231 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ1_M.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ1_S.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ2_M.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ2_S.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ2_XS.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ2_XXS.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ3_M.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ3_S.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ3_XS.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ3_XXS.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ4_NL.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-IQ4_XS.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q2_K.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q2_K_S.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q3_K_L.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q3_K_M.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q3_K_S.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q4_0.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q4_1.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q4_K_M.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q4_K_S.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q5_K_M.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q5_K_S.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.i1-Q6_K.gguf create mode 100644 Llama-3.1-8B-Instruct-Uz.imatrix.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..926f131 --- /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-3.1-8B-Instruct-Uz.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-Uz.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ1_M.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ1_M.gguf new file mode 100644 index 0000000..528240c --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ededfc431298c28b0a52b2b4ab3ca99b0ee18895231b74b0f575f0708d98eec +size 2161974304 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ1_S.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ1_S.gguf new file mode 100644 index 0000000..8de1ee6 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1d9b3e2b4afe930cd00e0b0534df6a7d08e9b120f4b6dbb8ae51e38cfc5623 +size 2019630112 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ2_M.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ2_M.gguf new file mode 100644 index 0000000..ec1749b --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b09aba9c72a153ffd74828cdd9485c1ba838e8cddadd9963f63e3e8ada3e997 +size 2948283424 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ2_S.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ2_S.gguf new file mode 100644 index 0000000..ae62f9d --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd440fdd43c8adfb2b206073bcd12a6aca18f0ce596523af921346df24b12e6 +size 2758491168 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ2_XS.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ2_XS.gguf new file mode 100644 index 0000000..372684f --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367eda360b81d86dec822e23f5a78365450a18bcc94e7d82699ded0b79dedd81 +size 2605784096 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ2_XXS.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..767fa94 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b685e61a974f52d0498abc15f8db640a670a1c97e250113a5b6a935a6784ee42 +size 2399214624 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ3_M.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ3_M.gguf new file mode 100644 index 0000000..6552a07 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d5fcd17a2c1fba098ca0db84ec1b32cfcba264b1f3afb437baba418607f394e +size 3784825888 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ3_S.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ3_S.gguf new file mode 100644 index 0000000..0daaeff --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c18da59361ab247da0f20f1345c2719e432aa48efade8988b72b79901f8994 +size 3682327584 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ3_XS.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ3_XS.gguf new file mode 100644 index 0000000..a0c4f67 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6db761fa8e24f99bbee0068316df7fa25d92d669867cb9d8d88b193cabfa9e65 +size 3518749728 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ3_XXS.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f8a1724 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f62e8d5bc50e04c06e63c2ee37f84ed23205d0e0971321944e54365b7df7e1 +size 3274914848 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ4_NL.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ4_NL.gguf new file mode 100644 index 0000000..758c4aa --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26f48f9d8ffacad6c2a0ae3bd02eb60233c2f6c2faf733299d23fd31f7b6219 +size 4677991456 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-IQ4_XS.gguf b/Llama-3.1-8B-Instruct-Uz.i1-IQ4_XS.gguf new file mode 100644 index 0000000..cf00cb0 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1fd960724ef5472df2841c3059e2622cb0e7b724c19a6ec8881e0d03e8f2193 +size 4447665184 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q2_K.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q2_K.gguf new file mode 100644 index 0000000..1b8249d --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8cd673028ca686900ac9c040c4cbb34751e3893a74002c61b63c3d03f33ef95 +size 3179133984 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q2_K_S.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4cedfd6 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:749cd4acd75955735670eefdbb6b9f847d015eb0c69902530e98a421be234153 +size 2988817440 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_L.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_L.gguf new file mode 100644 index 0000000..fe3dc3e --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa52271e8992d3d2ee1bc890fa6636ab365ed4e4b50daba3b44fd2228de9e84b +size 4321958944 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_M.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_M.gguf new file mode 100644 index 0000000..9bc45cb --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d622913147ab00be2ad5d5739b7b216cd41867403c2c4a691398bf04832c1336 +size 4018920480 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_S.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_S.gguf new file mode 100644 index 0000000..eda3a09 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42b9092c90d1399ed171e1b4cc21777e2cf5a714a6fac7b36430126b0d480f8f +size 3664501792 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q4_0.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q4_0.gguf new file mode 100644 index 0000000..b55998e --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285fe58bf98fa11783e9bd630ba0ac9a4c876a9f3ae8e1fc736fd4e437157180 +size 4675894304 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q4_1.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q4_1.gguf new file mode 100644 index 0000000..75f9e24 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d6c123d22ac3fe691fff3b0fead04d2531ef3521ab85d4e41ba695c1a14bc9 +size 5130255392 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q4_K_M.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4f077fa --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce2558822f292ee1662023036ff916b4ba129f0d4dbdcb757afcb8ea318a9c83 +size 4920736800 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q4_K_S.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q4_K_S.gguf new file mode 100644 index 0000000..cd3b284 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da7a6c2d87f0f08cfcb0b342698c4e794d04614e8bd93bc542fcd6d03e6e5dd +size 4692671520 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q5_K_M.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7282933 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf0ce8a65fceb38ca560cac94ca4402890c6bb40366240cddfb44b159d9df7d +size 5732989984 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q5_K_S.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q5_K_S.gguf new file mode 100644 index 0000000..68129a0 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e27eded576e82b33ad50d6e5d4cee88bbd124efac42ec52670cbdaf4ae51293d +size 5599296544 diff --git a/Llama-3.1-8B-Instruct-Uz.i1-Q6_K.gguf b/Llama-3.1-8B-Instruct-Uz.i1-Q6_K.gguf new file mode 100644 index 0000000..068201f --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a30a157b622d4c9f96ed41189e5eff0b2d0a823aff7fd8f3bc0d179b88352cad +size 6596008992 diff --git a/Llama-3.1-8B-Instruct-Uz.imatrix.gguf b/Llama-3.1-8B-Instruct-Uz.imatrix.gguf new file mode 100644 index 0000000..edab817 --- /dev/null +++ b/Llama-3.1-8B-Instruct-Uz.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:567cf1b9f7bb51fca30d16aeac0531f6a61940baa22195dd306e45fbdd03e2aa +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..14d61df --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: behbudiy/Llama-3.1-8B-Instruct-Uz +datasets: +- yahma/alpaca-cleaned +- behbudiy/alpaca-cleaned-uz +- behbudiy/translation-instruction +language: +- uz +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +- text-generation-inference +- summarization +- translation +- question-answering +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/behbudiy/Llama-3.1-8B-Instruct-Uz + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-Instruct-Uz-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-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-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uz-i1-GGUF/resolve/main/Llama-3.1-8B-Instruct-Uz.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. + +