From 5602f7dc72b3654d6003ea58e391a7925c1bc916 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 12 May 2026 18:19:24 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++ ...3.1-8B-UltraLong-1M-Instruct.i1-IQ1_M.gguf | 3 + ...3.1-8B-UltraLong-1M-Instruct.i1-IQ1_S.gguf | 3 + ...3.1-8B-UltraLong-1M-Instruct.i1-IQ2_M.gguf | 3 + ...3.1-8B-UltraLong-1M-Instruct.i1-IQ2_S.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-IQ2_XS.gguf | 3 + ...1-8B-UltraLong-1M-Instruct.i1-IQ2_XXS.gguf | 3 + ...3.1-8B-UltraLong-1M-Instruct.i1-IQ3_M.gguf | 3 + ...3.1-8B-UltraLong-1M-Instruct.i1-IQ3_S.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-IQ3_XS.gguf | 3 + ...1-8B-UltraLong-1M-Instruct.i1-IQ3_XXS.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-IQ4_NL.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-IQ4_XS.gguf | 3 + ...-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-Q2_K_S.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-Q3_K_L.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-Q3_K_M.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-Q3_K_S.gguf | 3 + ...-3.1-8B-UltraLong-1M-Instruct.i1-Q4_0.gguf | 3 + ...-3.1-8B-UltraLong-1M-Instruct.i1-Q4_1.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-Q4_K_M.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-Q4_K_S.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-Q5_K_M.gguf | 3 + ....1-8B-UltraLong-1M-Instruct.i1-Q5_K_S.gguf | 3 + ...-3.1-8B-UltraLong-1M-Instruct.i1-Q6_K.gguf | 3 + README.md | 76 +++++++++++++++++++ imatrix.dat | 3 + 27 files changed, 211 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XS.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XXS.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XS.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XXS.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_NL.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_XS.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_L.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_0.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_1.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_M.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_S.gguf create mode 100644 Llama-3.1-8B-UltraLong-1M-Instruct.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..d0b8f89 --- /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-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_M.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..b14f1e3 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f316b4fae8234b5eb30fad029a8132c6e3ab5afa7c4b6c5fd9ea659cf837aaf +size 2165189632 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_S.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..df270f3 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67089299370d3853e9f9e72a41365ca8cf9f236358b1cba994866fb28b03c337 +size 2022845440 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_M.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..bf3840d --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22556f49a4700569c29d677ac9917fc45b3c50c80f54cc20a3ff02dc49ef6e84 +size 2951818240 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_S.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..1b1cecd --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9b82b3f1dfda8ad5e04d258f9e4f6fd2073851bbde2cb25e3c5d012cfe5514 +size 2762025984 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XS.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..9baf3f4 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13cec00ee0eed29015e05aceec37563632d5025cd290a2a122e02257dcdc59bc +size 2608999424 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XXS.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bdcc0ac --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:166d810d30017cc384316c63a0a65ecf30c11a3a98dbd40cf8ec54ad3acfbdf3 +size 2402429952 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_M.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..d6cfdbf --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a88f3f26aef6da69649b007c088efab76fdfbaa93de434d4a47a87591881483 +size 3788778496 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_S.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..bfd051e --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64c3dc4e2ac68f0b9bc642a42f427e411e3ee0878578f1cc534befc1db737e16 +size 3686280192 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XS.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..fec444a --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af4984da0affd66aac95ce961e3616409d79a56104775a61086e8ce115cfa131 +size 3522702336 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XXS.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ce8ac35 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:176a058f2249a6ede82ed06bac452b80fa11e17856f4c2702d7e1946732e8b34 +size 3278449664 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_NL.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..7818f57 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e167864a384f5e81836c12c17b8477242020a04d719ac160215f2d39b3fde9f +size 4682361856 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_XS.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..2fc212c --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ac5d680e7df135a5efc3a3a54870614d1863f910024f4cf809138014c5b174 +size 4451937280 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..9868e55 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a352940f6338cdd35d688367491bdd0a7a57a2417d639cedf1ad9c6052703f +size 3182767104 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K_S.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0a2144d --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8b04322743ae37a6ccd7bd7b2f4448877400a2bf0a24864a48569017519aaaf +size 2992450560 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_L.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..18e4631 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce34e22e8f3279096c774f16972a47aaf2a28a5c223d5d94929c81fb3204aa1 +size 4325911552 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_M.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e7f471e --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c24d944a5cd5b944278218748bc4e7054f8da36da6649c1f3efb9188d7e1be2c +size 4022873088 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_S.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..decdad1 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c8c7aa640b4cda4d706661258f0c04f7184c19e939d926671af75e804713725 +size 3668454400 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_0.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..c2f5eff --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86cf8457714fe23d953ba3ba0c695ce3d88430b30ea178a9f90f880da2b6f63a +size 4680264704 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_1.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..c3c310b --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e70a9b7c6a31565582a349a44861880d3fb70d090b50fb266cc4d5cefd8b3b +size 5134822400 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_M.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8c524a1 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6738cf4023449c45c499295ed1de320fa881d3d041fa0ab5b57595cf73a1545f +size 4925107200 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_S.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..bcd5f98 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:792f0f232c8a74c1485ce6861952f369256d156f64906ad721aa876444dd75ca +size 4697041920 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_M.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..e66196d --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c63899cc0852b4eae02b2fd5d03eaaa8015f2ed956c9097e93e591dfbd04296 +size 5737753600 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_S.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5683fa8 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:665de4d7204e2595cf67eb57ea20fa917b3c90fc1bef87fb54fa85fb177807be +size 5604060160 diff --git a/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q6_K.gguf b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..4b690a0 --- /dev/null +++ b/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e40b58059a50e27de9d2bdf41b83fb328965788f3086c1936deab0450bf23bdb +size 6601190400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9f518c4 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraLong-1M-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-UltraLong-1M-Instruct.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..8d9d4cd --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfead29dc6a754d6b8e888c3a36e084ab778bc775b877ae98e99ff7d2f56dc13 +size 4988157