From 9dcaca06dccc2b421a46d3634323df2367ffdd22 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 18 May 2026 14:24:18 +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/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++ ....2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_M.gguf | 3 + ....2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_S.gguf | 3 + ....2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_M.gguf | 3 + ....2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_S.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XS.gguf | 3 + ...-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XXS.gguf | 3 + ....2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_M.gguf | 3 + ....2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_S.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XS.gguf | 3 + ...-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XXS.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_NL.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_XS.gguf | 3 + ...3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K_S.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_L.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_M.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_S.gguf | 3 + ...3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_0.gguf | 3 + ...3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_1.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_M.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_S.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_M.gguf | 3 + ...2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_S.gguf | 3 + ...3.2-TaiPhone-3B-Instruct-v0.2.i1-Q6_K.gguf | 3 + ...3.2-TaiPhone-3B-Instruct-v0.2.imatrix.gguf | 3 + README.md | 89 +++++++++++++++++++ 27 files changed, 224 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_M.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_S.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_M.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_S.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XS.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XXS.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_M.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_S.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XS.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XXS.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_NL.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_XS.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K_S.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_L.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_M.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_S.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_0.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_1.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_M.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_S.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_M.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_S.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q6_K.gguf create mode 100644 Llama3.2-TaiPhone-3B-Instruct-v0.2.imatrix.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..efee321 --- /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 +Llama3.2-TaiPhone-3B-Instruct-v0.2.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_M.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_M.gguf new file mode 100644 index 0000000..15c4b3a --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d3b1b65c2da4387106eb9baba0756a9db1715a68f724cb1c8e27723f5704799 +size 924192096 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_S.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_S.gguf new file mode 100644 index 0000000..e4fedae --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b63d4430f66f2f24f656fdef31ab6795ef6d02ce70b04894a7292dca9c416e +size 868158816 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_M.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_M.gguf new file mode 100644 index 0000000..2be9c9a --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9783b99dd30b541d5000d3e81d845cea5980885d5a8c1bec8699a6cb7ff3af76 +size 1229032800 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_S.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_S.gguf new file mode 100644 index 0000000..c963df0 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcef4ad05f92ac5080508a580d23f60a1ea9cb28d1c0dbaf859d6e0a6fbacedb +size 1154321760 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XS.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..58274c6 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9ac412406146d2a1545b7d0297c12dadce1f63928daa671bda3f96fea6b21f +size 1100549472 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XXS.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..76b0932 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8d29f73a15e05bb548521aa982c737f94265284ff045f11b1f99cc3b65cdc0 +size 1017580896 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_M.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_M.gguf new file mode 100644 index 0000000..da0e149 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4407826b0e36c3a6d493bef8e530e7344f17aa297872b9fd29494bf407fe9d99 +size 1599669600 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_S.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_S.gguf new file mode 100644 index 0000000..0df02b4 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e7679edb63f9e6eb5385ad307901588500404973c700288c37e03096d4b565c +size 1542849888 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XS.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..1702611 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0423246c59bfccfe1cba0f5e9052f8994a57c8d779b33e4741023af6512e2b55 +size 1476789600 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XXS.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..fd1f952 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11d432225c8d8284fc7431cca9f00212a60694cbde8d0565e8680c444369aa7a +size 1348767072 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_NL.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_NL.gguf new file mode 100644 index 0000000..d451891 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d1d397271fc16b6165efe175f3430f41e2a244457b5a32bc9038280d1acf95 +size 1917191520 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_XS.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..f822543 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab2ead90f1f1c548214e6fb4939f2bf9cbef0f3b098e370c22376b8ed75ae581 +size 1829111136 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K.gguf new file mode 100644 index 0000000..aa8a43c --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfdc324942e9aa30a042cff036fbe38057077f5826c7a69825e6aff2eb400fe7 +size 1363936608 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K_S.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K_S.gguf new file mode 100644 index 0000000..1927fd3 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:761603143f55f58c87d225a0daedbbc2a5ae5e6ba0410c5bb3119e1243df1cb1 +size 1274283360 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_L.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e2caf4a --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a05f3b8ced17c4842d61852c900c5deadf54cc2d2ec63148192734d60ce50a14 +size 1815348576 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_M.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..be97bd6 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:107ac9b5bdb9006841dcc6188e3e3d92890d910a0ddca3beed1aceb76ce34d0b +size 1687160160 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_S.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f605498 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a70851e5c545eda0702501020e12efdbcb897d6f80f6b2b402ce02c334afaf1 +size 1542849888 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_0.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_0.gguf new file mode 100644 index 0000000..3322c40 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fd29008bde2b30a68a099fad5dcd46b06e01d1c6774d3ddc225bd8950424629 +size 1921910112 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_1.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_1.gguf new file mode 100644 index 0000000..477de36 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa6a7aae43c980bb4ea4cb94b78ca53e6222d48e9bc358b579e3cf9447702f2f +size 2093352288 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_M.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..30c5c2f --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fcf6d511be96d0ae5bb2ed35342f904345d1bdda5da9124ff35e5fec276d10e +size 2019378528 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_S.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d7f2682 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3e02d84d2dc8dd932773b3b00812e2d7c125145f03fa21fb7f4d2b5b0cc012 +size 1928201568 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_M.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..aca53d0 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c69ed273dd43914131934f2d44fe266c3167b260c080ddb837d1e9171775ae14 +size 2322154848 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_S.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ad383ca --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2778847db1565ae9a6477b1c96329010cc181127afe1f5dc5dcac47c69a02e6 +size 2269513056 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q6_K.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q6_K.gguf new file mode 100644 index 0000000..319f229 --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25e02fdda957098eab1d6fea2367099e3b9a0f99580adff5578a0bcca43ae4b8 +size 2643854688 diff --git a/Llama3.2-TaiPhone-3B-Instruct-v0.2.imatrix.gguf b/Llama3.2-TaiPhone-3B-Instruct-v0.2.imatrix.gguf new file mode 100644 index 0000000..21872cf --- /dev/null +++ b/Llama3.2-TaiPhone-3B-Instruct-v0.2.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:994f035b9e145b7f95f13388f31cd35e76b2a25b93f692a4ee814bd22a436546 +size 3012064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fbb83bb --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: aqweteddy/Llama3.2-TaiPhone-3B-Instruct-v0.2 +language: +- zh +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- slm +- taiwan +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/aqweteddy/Llama3.2-TaiPhone-3B-Instruct-v0.2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-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/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-i1-GGUF/resolve/main/Llama3.2-TaiPhone-3B-Instruct-v0.2.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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. + +