From 3b1773b4be10998f548891df949b01e2e2fca067 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 18 May 2026 02:51:44 +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-3-8B-Instruct-Gradient-1048k-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++++ ...3-8B-Instruct-Gradient-1048k.i1-IQ1_M.gguf | 3 + ...3-8B-Instruct-Gradient-1048k.i1-IQ1_S.gguf | 3 + ...3-8B-Instruct-Gradient-1048k.i1-IQ2_M.gguf | 3 + ...3-8B-Instruct-Gradient-1048k.i1-IQ2_S.gguf | 3 + ...-8B-Instruct-Gradient-1048k.i1-IQ2_XS.gguf | 3 + ...8B-Instruct-Gradient-1048k.i1-IQ2_XXS.gguf | 3 + ...3-8B-Instruct-Gradient-1048k.i1-IQ3_M.gguf | 3 + ...3-8B-Instruct-Gradient-1048k.i1-IQ3_S.gguf | 3 + ...-8B-Instruct-Gradient-1048k.i1-IQ3_XS.gguf | 3 + ...8B-Instruct-Gradient-1048k.i1-IQ3_XXS.gguf | 3 + ...-8B-Instruct-Gradient-1048k.i1-IQ4_XS.gguf | 3 + ...-3-8B-Instruct-Gradient-1048k.i1-Q2_K.gguf | 3 + ...-8B-Instruct-Gradient-1048k.i1-Q3_K_L.gguf | 3 + ...-8B-Instruct-Gradient-1048k.i1-Q3_K_M.gguf | 3 + ...-8B-Instruct-Gradient-1048k.i1-Q3_K_S.gguf | 3 + ...-3-8B-Instruct-Gradient-1048k.i1-Q4_0.gguf | 3 + ...B-Instruct-Gradient-1048k.i1-Q4_0_4_4.gguf | 3 + ...B-Instruct-Gradient-1048k.i1-Q4_0_4_8.gguf | 3 + ...B-Instruct-Gradient-1048k.i1-Q4_0_8_8.gguf | 3 + ...-8B-Instruct-Gradient-1048k.i1-Q4_K_M.gguf | 3 + ...-8B-Instruct-Gradient-1048k.i1-Q4_K_S.gguf | 3 + ...-8B-Instruct-Gradient-1048k.i1-Q5_K_M.gguf | 3 + ...-8B-Instruct-Gradient-1048k.i1-Q5_K_S.gguf | 3 + ...-3-8B-Instruct-Gradient-1048k.i1-Q6_K.gguf | 3 + README.md | 79 +++++++++++++++++++ imatrix.dat | 3 + 27 files changed, 214 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_M.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_S.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_M.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_S.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XS.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XXS.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_M.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_S.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XS.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XXS.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-IQ4_XS.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q2_K.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_L.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_M.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_S.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_4.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_8.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_8_8.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_M.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_S.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_M.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_S.gguf create mode 100644 Llama-3-8B-Instruct-Gradient-1048k.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..8b7f266 --- /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-3-8B-Instruct-Gradient-1048k.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_M.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_M.gguf new file mode 100644 index 0000000..19a7a70 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc57e2c1cec978d085fb7a4a44785c0fa023b28b261bae5c19780533753ce1f +size 2161972608 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_S.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_S.gguf new file mode 100644 index 0000000..2e3a994 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5557820f8a479b5f19e2fbaac0413f449714746cb52c152920024d9279b7129 +size 2019628416 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_M.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_M.gguf new file mode 100644 index 0000000..0b194cb --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2a26db9591d8aae519a4447f138499b75fe409fbbd7a2cdae7975ff15137c21 +size 2948281728 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_S.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_S.gguf new file mode 100644 index 0000000..aa33712 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc29c86c62cf2d05fc1abc492307ce0b52d5f02736dad22e165f8cbaed5002fc +size 2758489472 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XS.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XS.gguf new file mode 100644 index 0000000..cc1c360 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a64ff56a2ef871b9a8f867b78156e41a35e476ed8257c0a79b6beec927ae058 +size 2605782400 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XXS.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e507af4 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a84706eeb3419f8e3b920cf02c489b952ddd4759d2e9886a7ecec18c5cbc43 +size 2399212928 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_M.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_M.gguf new file mode 100644 index 0000000..1517df2 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17194475e349e39250988dc1ed9b29b50621ff8e85cfb16f65c37b0becd24fae +size 3784824192 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_S.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_S.gguf new file mode 100644 index 0000000..546a9b4 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e0f68d09349cc11eaa931d74832c4ff7ce57a1bfa59ed1e2d69243289447e7c +size 3682325888 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XS.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XS.gguf new file mode 100644 index 0000000..421e78b --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42688076d57df863aa423d4f5e043154a688b6a6f8b12f13726227a11e7b5959 +size 3518748032 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XXS.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..93f8b38 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f87eca2f9366866bb0ad0d7dfa6dfb6ce1daf094292dc330a1befefa4eb7f560 +size 3274913152 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ4_XS.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6462ad8 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe83d65684a854fdfb0aca3c4713ced388ea843b97ef89e94c8a4dc80570b89 +size 4447663488 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q2_K.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q2_K.gguf new file mode 100644 index 0000000..9bc7926 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af28994c042fd36646c7abbc7b80cb37ecd726189b6a2cfd83029c30adf1155 +size 3179132288 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_L.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f353cdf --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a65b962d2890f49a69107f5a5e772b4c405324032ab088d67cfb08403d6e3b9d +size 4321957248 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_M.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_M.gguf new file mode 100644 index 0000000..820aada --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11edad809101d0bb7163b82af4c1c6eae4b7ea4ce6e2d632137ffec2974a1e5d +size 4018918784 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_S.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_S.gguf new file mode 100644 index 0000000..af77a60 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ccc69d22f96786a5ae333be95c2a8d0ce937430ad1feb99e7d52a87a737ef7 +size 3664500096 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0.gguf new file mode 100644 index 0000000..2968c18 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:300670515b9429767a3f4cedd096fbc38f61fd67df9014d6a18dffce4f1aeef0 +size 4675892608 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_4.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..eadb51e --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a93809d1c657f9805dca9583227abeeae93d070492b0ec1cf43acad37edf3af +size 4661212544 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_8.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..35f9f7b --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4f185ef9260fdf9a0fb256841e31720a049ded07e1e38f6e764041011038039 +size 4661212544 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_8_8.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..b42d23e --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b790ac1b4b0e54850ba9aed384f71b71b5d5e6a8806a46add07146eed0f9ac4 +size 4661212544 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_M.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f61ccb6 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def815e23d2f5e5ce05efb41005524e2a706fa062792f30c3f14328336c3e2c4 +size 4920735104 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_S.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_S.gguf new file mode 100644 index 0000000..004ba2d --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe82eef6b57eb2bcf6877478fb8e2821de26433fa12c3c866115fd73c8f510a +size 4692669824 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_M.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_M.gguf new file mode 100644 index 0000000..1408c72 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362e6270e54304298d1ba020b330947f9253f20134e39ad9dcf31b6f042ad806 +size 5732988288 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_S.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5edd400 --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3adc3bcc0c3396c3d8d0177c02db83f03a0713c437200f2584aa25b6577db39c +size 5599294848 diff --git a/Llama-3-8B-Instruct-Gradient-1048k.i1-Q6_K.gguf b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q6_K.gguf new file mode 100644 index 0000000..feca4ab --- /dev/null +++ b/Llama-3-8B-Instruct-Gradient-1048k.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65755236fb8497f86f603752a8abd2067ee415d13de96822a9527c362cc25108 +size 6596007296 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1997a44 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: gradientai/Llama-3-8B-Instruct-Gradient-1048k +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- meta +- llama-3 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-1048k + + +static quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-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-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.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-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.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-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Gradient-1048k-i1-GGUF/resolve/main/Llama-3-8B-Instruct-Gradient-1048k.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..d3415a5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab7b04b05d622d2b9a2a7c4efd6ed17fdb576f12c2c69c68b809e6ebde67ed65 +size 4988157