From a16603650e49fe09310c74a9a54bb9b4db079b00 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 4 Jun 2026 20:16:17 +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/Qwen2.5-7B-ThaiInstruct-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++++ Qwen2.5-7B-ThaiInstruct.i1-IQ1_M.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-IQ1_S.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-IQ2_M.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-IQ2_S.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-IQ2_XS.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-IQ2_XXS.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-IQ3_M.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-IQ3_S.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-IQ3_XS.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-IQ3_XXS.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-IQ4_XS.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q2_K.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q3_K_L.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q3_K_M.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q3_K_S.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q4_0.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_4.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_8.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q4_0_8_8.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q4_K_M.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q4_K_S.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q5_K_M.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q5_K_S.gguf | 3 + Qwen2.5-7B-ThaiInstruct.i1-Q6_K.gguf | 3 + README.md | 84 ++++++++++++++++++++++++ imatrix.dat | 3 + 27 files changed, 219 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ1_M.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ1_S.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ2_M.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ2_S.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ2_XS.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ2_XXS.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ3_M.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ3_S.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ3_XS.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ3_XXS.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-IQ4_XS.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q2_K.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q3_K_L.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q3_K_M.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q3_K_S.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q4_0.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_4.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_8.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q4_0_8_8.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q4_K_M.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q4_K_S.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q5_K_M.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.i1-Q5_K_S.gguf create mode 100644 Qwen2.5-7B-ThaiInstruct.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..4ce0b99 --- /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 +Qwen2.5-7B-ThaiInstruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ThaiInstruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ1_M.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..5ebd34d --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f80bc82ec96464a769f537a1b36f289ea36977967411d021e7ee11e004f7593 +size 2042197216 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ1_S.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..e4cdeca --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f501438b03e85402d2875012ae1d6a9735003cbcb85e5c74c6e527914b620f +size 1903668448 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ2_M.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..1034a19 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a204d0bc75d811e8cb35e8640b650275a36498348c251c1cd9f38eaf403fb255 +size 2780343520 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ2_S.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..bd52209 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1e113ec1a0ea1992c4c66e8d2605b730e3ff180fb56fb84f5e3a59fb9c843c +size 2595638496 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ2_XS.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..0def833 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14bfaf0e5b0540fe0c2d08769033e984e87b0403b1a0a9b50c1bcede8fa8b2ee +size 2469022944 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ2_XXS.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1661d10 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe771c67c3a12a54479fa430cf176031c967b81a5204d84cc37b9d0fc43e192 +size 2273078496 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ3_M.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..37ee063 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11df35b98324c3aadc4a901158da4c8e35f74e5becb2ce40e9c8f6af4bb873a0 +size 3574013152 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ3_S.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..e68782d --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456cf6f9fca448be12c2fc05d23c30bf427f9aeb7d30d315e839c416ea84051c +size 3499193568 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ3_XS.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..cc48816 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bffa6317dae0d7488a7b7eac8dd84c61401f452ba24fe2fb3b6e437c0d04e0b1 +size 3346257120 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ3_XXS.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ba8a65b --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7a9e97a299aed1e804f907aa5aaa497263b5a63d4fe237157fdee3d49e1fb7 +size 3114515680 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-IQ4_XS.gguf b/Qwen2.5-7B-ThaiInstruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..f3e0cf7 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9361d51cf0f17ff8078ce515cebbfd275767a691881fcb357f01dd5bde69ed51 +size 4218473696 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q2_K.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q2_K.gguf new file mode 100644 index 0000000..fe8d541 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa0a489c0f1d56f411112983516c0f8925481283892e1ab03aa6ddf0046cbaf +size 3015941344 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_L.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..74c41e1 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ab71e63eac7991fb8b54927a0212b00462109ebbcd34f4b1d1916f784ca4564 +size 4088460512 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_M.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..8e472be --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbe1a2cdfb360692e9c8d3b0fb740c2a8885028a30471a234710195f194cd243 +size 3808392416 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_S.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..14a536f --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f76060e7595c8cf05235879a1828ca5ab8de0567fc6cce8e1bb2d56afbb4b8b +size 3492369632 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q4_0.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q4_0.gguf new file mode 100644 index 0000000..dc26155 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7188f69012908508b53bff10706aec8642519e6586319e33e9efceeaa524ba +size 4444122336 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_4.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..b0effa9 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be921f8fb48a952782b3a1b6f71014e52574410b665a35e8b3ddb283a7275885 +size 4431391968 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_8.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..4566e87 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9c6c0459776fb89e7fbb2d670ed0c60c5bc9757d0be6a26b66141ee0529c53e +size 4431391968 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_8_8.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..f175117 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5dcb1c41f6357d400b620a6077527e11822d0f8646f818b3dc93729c4809f9c +size 4431391968 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q4_K_M.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ea7677b --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1593b2d12860c5f11c40fd0c7e99b5792bdf8cee4fed777a37a5a9399a2a4e72 +size 4683074784 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q4_K_S.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..cbcf1aa --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce67b1fbaabcbe422f5232913667660f911095e8f9c780009b506f04227d0064 +size 4457770208 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q5_K_M.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f4400a9 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a73704e21cfa4902e0477a1cbe040f9666c231a069b07243d11f31b79d2ce6e9 +size 5444832480 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q5_K_S.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..f8067b5 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37f7eb9fa90c32db9a13652f660387960b2f9d5092c6993f3d519ce8da775a8e +size 5315177696 diff --git a/Qwen2.5-7B-ThaiInstruct.i1-Q6_K.gguf b/Qwen2.5-7B-ThaiInstruct.i1-Q6_K.gguf new file mode 100644 index 0000000..e9a6358 --- /dev/null +++ b/Qwen2.5-7B-ThaiInstruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2caca3033eb376fe6f48c7d4a97d0909b8f78367c65e3e75b1cb3a6668b6f352 +size 6254200032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9c0dbe1 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Konthee/Qwen2.5-7B-ThaiInstruct +datasets: +- airesearch/WangchanThaiInstruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Konthee/Qwen2.5-7B-ThaiInstruct + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-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/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.5 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.5 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ThaiInstruct-i1-GGUF/resolve/main/Qwen2.5-7B-ThaiInstruct.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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..b88378d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944bed142ecde6c2147fab21634a9549f682f21fcbea81fdaddf2de653859bb5 +size 4536665