From 85a5f23eb3f4f0b633fc50ecf1a58cf5b631cb4d Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 14 Jun 2026 00:28:16 +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-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++ ...emotron-Nano-4B-v1.1-heretic.i1-IQ1_M.gguf | 3 + ...emotron-Nano-4B-v1.1-heretic.i1-IQ1_S.gguf | 3 + ...emotron-Nano-4B-v1.1-heretic.i1-IQ2_M.gguf | 3 + ...emotron-Nano-4B-v1.1-heretic.i1-IQ2_S.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-IQ2_XS.gguf | 3 + ...otron-Nano-4B-v1.1-heretic.i1-IQ2_XXS.gguf | 3 + ...emotron-Nano-4B-v1.1-heretic.i1-IQ3_M.gguf | 3 + ...emotron-Nano-4B-v1.1-heretic.i1-IQ3_S.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-IQ3_XS.gguf | 3 + ...otron-Nano-4B-v1.1-heretic.i1-IQ3_XXS.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-IQ4_NL.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-IQ4_XS.gguf | 3 + ...Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-Q2_K_S.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-Q3_K_L.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-Q3_K_M.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-Q3_K_S.gguf | 3 + ...Nemotron-Nano-4B-v1.1-heretic.i1-Q4_0.gguf | 3 + ...Nemotron-Nano-4B-v1.1-heretic.i1-Q4_1.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-Q4_K_M.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-Q4_K_S.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-Q5_K_M.gguf | 3 + ...motron-Nano-4B-v1.1-heretic.i1-Q5_K_S.gguf | 3 + ...Nemotron-Nano-4B-v1.1-heretic.i1-Q6_K.gguf | 3 + ...Nemotron-Nano-4B-v1.1-heretic.imatrix.gguf | 3 + README.md | 98 +++++++++++++++++++ 27 files changed, 233 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_M.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_S.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_M.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_S.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XS.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XXS.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_M.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_S.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XS.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XXS.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_NL.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_XS.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K_S.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_L.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_M.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_S.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_0.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_1.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_M.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_S.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_M.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_S.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q6_K.gguf create mode 100644 Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.imatrix.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6ae3422 --- /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-Nemotron-Nano-4B-v1.1-heretic.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_M.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_M.gguf new file mode 100644 index 0000000..b639dba --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b08c0f14e3ece7371f2912f23d30d4f5bf9d10d2b017f69c96a412403b482b +size 1286259104 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_S.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_S.gguf new file mode 100644 index 0000000..4b0a51e --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5761963d5c618c490e6323871a9de3fe51cf0ba4108376c6bb3d681f6b9310e +size 1213415840 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_M.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_M.gguf new file mode 100644 index 0000000..136ea3c --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f234fb079106cc374809ef6d26807c715ac73025463ab42e2cb9c1564cde728a +size 1722636704 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_S.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_S.gguf new file mode 100644 index 0000000..28d455f --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f2f27b835fd9f85642837738345931dc53f64bdfa74515cff25ea4d335ec944 +size 1625512352 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XS.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XS.gguf new file mode 100644 index 0000000..10f5adf --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19ba6999da89ba26cd2567f4fe57a46230b9146128956beb009e8ed3554e0526 +size 1517371808 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XXS.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..7933980 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e8d074c3ece896bf0374a6c2f28cbcc324778e87dccb81c596e87659704533 +size 1407664544 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_M.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_M.gguf new file mode 100644 index 0000000..a159ccd --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bf9bbbaac33f44a71fb2d0c8b4963620508ff9125f62a731ec7cdcb7a543a4d +size 2183418272 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_S.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_S.gguf new file mode 100644 index 0000000..b8df7ec --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dc6e5133faf24fa315a5a90c1ee7744a7b89fa240e787e02326ad7b67df06c1 +size 2114900384 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XS.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XS.gguf new file mode 100644 index 0000000..5348832 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a8df18b68d6fec22084d8962fe7f4570c946703a7322f3a6219fc138889552 +size 2027606432 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XXS.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..79564ce --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeaa0a9335d37a63e2aa1416e518ab3a69b70528ecdeff94af737e03cf3772e6 +size 1880119712 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_NL.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_NL.gguf new file mode 100644 index 0000000..b61c620 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a400704a4f0fbd05b9cec522c52fc2d3dbcf1e3cd2614d21fda962608f378364 +size 2661108128 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_XS.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ed3518d --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f51f5368e1d929d4f80d14a164d5b22fd6f8b202b92bb107ceaecbfff4abbe +size 2535549344 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K.gguf new file mode 100644 index 0000000..6bc175e --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cdcbb3134bc706da72414d2d704d4324cf3efd283c0d9c0f9bc66049543dead +size 1839741344 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K_S.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K_S.gguf new file mode 100644 index 0000000..8e03f83 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd09b4c4d0866cdd18f845132ab99e2312d54066dec1053168bbb6daeaac234e +size 1733376416 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_L.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d505114 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86d1efa8a3f6310f89633b0b0f863ccff2df516933015dcec4ce96f33955912f +size 2464862624 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_M.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_M.gguf new file mode 100644 index 0000000..430076a --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f64b702e4e136ebe2207344cd30708c2a92936c96c660e1c27f44a1d8408f842 +size 2296566176 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_S.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1e71571 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6058b1e15a202036db2d4e42abde317b66880589fbd208dfb0ef2e3b2378b888 +size 2101531040 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_0.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_0.gguf new file mode 100644 index 0000000..07052c6 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b43a1cfb9d239eb89e96d054a614d95db8311d558c866282749a981176168706 +size 2655603104 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_1.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_1.gguf new file mode 100644 index 0000000..3694d8b --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d25534cdde10829e141f56c27ba8ff1317a7605fecdc41ebaf0bbe7a4dcd170d +size 2905934240 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_M.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_M.gguf new file mode 100644 index 0000000..0739a7d --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd9f05eeed17b23493a7ac3e69e406bcbcd261c96ec0b19d107da155bdd2368 +size 2778286496 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_S.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e6db4ff --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c80102518013eb839118cba8f4d7398d017e415dd4707ad87952e72d3ea303 +size 2664253856 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_M.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_M.gguf new file mode 100644 index 0000000..d28b3f6 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0290e83a5d6558e6414da43a65bd5841c7623f8488dde8e4da2bf2033384f49d +size 3230189984 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_S.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_S.gguf new file mode 100644 index 0000000..70d6fc0 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07205a82a85516b0a9759d047faa730ca5b8197602d2a857ae3bbc99dbc4e1a2 +size 3163343264 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q6_K.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q6_K.gguf new file mode 100644 index 0000000..1d36837 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579fcdcc4ed3c13267bd84e1fd5a46e068e04aa364f0ee15939aceab2f60f8dd +size 3710337440 diff --git a/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.imatrix.gguf b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.imatrix.gguf new file mode 100644 index 0000000..2ee9cf6 --- /dev/null +++ b/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:302146c670d6836d5ae3dc79261453b163e710ce94b7a5475b7826c74498b0e4 +size 3704480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..432a5ea --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +base_model: hardcoreerik/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic +datasets: +- nvidia/Llama-Nemotron-Post-Training-Dataset +language: +- en +library_name: transformers +license: other +license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ +license_name: nvidia-open-model-license +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nvidia +- llama-3 +- pytorch +- heretic +- uncensored +- decensored +- abliterated +- reproducible +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/hardcoreerik/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-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-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_S.gguf) | i1-IQ1_S | 1.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ1_M.gguf) | i1-IQ1_M | 1.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_S.gguf) | i1-IQ2_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ2_M.gguf) | i1-IQ2_M | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q2_K.gguf) | i1-Q2_K | 1.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_S.gguf) | i1-IQ3_S | 2.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ3_M.gguf) | i1-IQ3_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_0.gguf) | i1-Q4_0 | 2.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q4_1.gguf) | i1-Q4_1 | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic-i1-GGUF/resolve/main/Llama-3.1-Nemotron-Nano-4B-v1.1-heretic.i1-Q6_K.gguf) | i1-Q6_K | 3.8 | 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. + +