From 1945c6cc7af57ff8716c02107f42c0512ab2e7c7 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 18 May 2026 13:54:37 +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-MultiReflection-Instruct-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++ ...-8B-MultiReflection-Instruct.i1-IQ1_M.gguf | 3 + ...-8B-MultiReflection-Instruct.i1-IQ1_S.gguf | 3 + ...-8B-MultiReflection-Instruct.i1-IQ2_M.gguf | 3 + ...-8B-MultiReflection-Instruct.i1-IQ2_S.gguf | 3 + ...8B-MultiReflection-Instruct.i1-IQ2_XS.gguf | 3 + ...B-MultiReflection-Instruct.i1-IQ2_XXS.gguf | 3 + ...-8B-MultiReflection-Instruct.i1-IQ3_M.gguf | 3 + ...-8B-MultiReflection-Instruct.i1-IQ3_S.gguf | 3 + ...8B-MultiReflection-Instruct.i1-IQ3_XS.gguf | 3 + ...B-MultiReflection-Instruct.i1-IQ3_XXS.gguf | 3 + ...8B-MultiReflection-Instruct.i1-IQ4_XS.gguf | 3 + ...1-8B-MultiReflection-Instruct.i1-Q2_K.gguf | 3 + ...8B-MultiReflection-Instruct.i1-Q3_K_L.gguf | 3 + ...8B-MultiReflection-Instruct.i1-Q3_K_M.gguf | 3 + ...8B-MultiReflection-Instruct.i1-Q3_K_S.gguf | 3 + ...1-8B-MultiReflection-Instruct.i1-Q4_0.gguf | 3 + ...-MultiReflection-Instruct.i1-Q4_0_4_4.gguf | 3 + ...-MultiReflection-Instruct.i1-Q4_0_4_8.gguf | 3 + ...-MultiReflection-Instruct.i1-Q4_0_8_8.gguf | 3 + ...8B-MultiReflection-Instruct.i1-Q4_K_M.gguf | 3 + ...8B-MultiReflection-Instruct.i1-Q4_K_S.gguf | 3 + ...8B-MultiReflection-Instruct.i1-Q5_K_M.gguf | 3 + ...8B-MultiReflection-Instruct.i1-Q5_K_S.gguf | 3 + ...1-8B-MultiReflection-Instruct.i1-Q6_K.gguf | 3 + README.md | 90 +++++++++++++++++++ imatrix.dat | 3 + 27 files changed, 225 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_M.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_S.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_M.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_S.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XS.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XXS.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_M.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_S.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XS.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XXS.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-IQ4_XS.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q2_K.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_L.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_M.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_S.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_4.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_8.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_8_8.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_M.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_S.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_M.gguf create mode 100644 Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_S.gguf create mode 100644 Llama-3.1-8B-MultiReflection-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..e345b12 --- /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-MultiReflection-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_M.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..22c97d3 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37b163fe180d83117eaac7c778234e78219e754f08f43725ac39b4bad7467301 +size 2161977664 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_S.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..13a2a22 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd788c1056a551215994fb6b082e69f51ffca74b7d04055a240b289a054ad91b +size 2019633472 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_M.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..76b82d5 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7326c026944925b2c93d7ff8e509359f0aa84db1cf921a828c8696e4c71c0e89 +size 2948286784 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_S.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..176ba11 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7576e60f096512c02b40aaa1f70911c1d2c01628be9adc49b42b0de5d82bf413 +size 2758494528 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XS.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..13dd59c --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e003f286d3480ad55b1f31cc6b802c8c82b91681a3b71b3798bb1e40d8fc80 +size 2605787456 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XXS.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..39ed2e9 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61bc19d1a9a786a9068a902704eddb07f31dacbc8ff7ffd69afb59f000232b4 +size 2399217984 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_M.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..91acb7c --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03473f5bbe1430788798949b1c2313c35212a3498166a46f1bbcb44cab0300f3 +size 3784829248 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_S.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..4b7038a --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4961f11a0dbe212c141cd63d570378483775d7eed9e80d0b0966a76c3dc27c3a +size 3682330944 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XS.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d30874a --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1696da24e3ff5b0bdc24cf5ab8ac4aefc1cab3c80976740d97ef50ef55bef160 +size 3518753088 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XXS.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..72ef003 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:283b82c9e163cd98931ff05797c4b7f33f8c395a3ad05307bcb985f38b2b063b +size 3274918208 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ4_XS.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b04074c --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c571023ba0d69aad0f29564414c51c06ad627c8cd4913fa6db099923c2624681 +size 4447668544 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q2_K.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..2e41c6c --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5c7bbbe51f219c66c081542303ddb6a11dbd7f1a29875bf8e589edbd237783 +size 3179137344 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_L.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..426a9ec --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf118ce742d7fb92f21805f43c5459f0ee77aa516404e256256d916b1b28c40 +size 4321962304 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_M.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4b4633f --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28cf297270128269a141589ca52eb9566c74381112d2e4e8706b0276a3343450 +size 4018923840 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_S.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f40bc6a --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85c315ffdb3e9559298abe8e603601fea9d41aa0976577c82f4b21edddfbb6d3 +size 3664505152 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..2176b07 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4cba7764572cbc06f5464550b463a13be752dfa00bae9cc09abb471434af0e4 +size 4675897664 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_4.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..d782d53 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a726b8d7c6694a4fc360a2f3adbbd370a8aca0ec506d4ac2bd0aa6b7460a54dd +size 4661217600 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_8.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..14f5f8d --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f017d94201bc0b994ab618c3387ed8353a4a16e08ea79e1ca17f1848ce5f46 +size 4661217600 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_8_8.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..e0f3353 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dffdedd31579a97e4e876beb2f11d234327d682f0f186fdbd1649abd00d59e8 +size 4661217600 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_M.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..15b2432 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebe559182939cfe4a4f87a3ed82471d7d879628397a94a7e6905930b0340a91e +size 4920740160 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_S.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e68fb25 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c35dedeeb4f60a6cc12bc2f0c2497e88bdf3bead7eefd723c638984d4f37599 +size 4692674880 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_M.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c9470f1 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1bca14b2f19ada56333ad755e633820248a32c4de6a9399f3e027f44f35cc05 +size 5732993344 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_S.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d730cd9 --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea7ed0f4052af71fe628162c90b3216a6b82557500b8b90cfa9db529890258d +size 5599299904 diff --git a/Llama-3.1-8B-MultiReflection-Instruct.i1-Q6_K.gguf b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..6d0bb1d --- /dev/null +++ b/Llama-3.1-8B-MultiReflection-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32f7055ee7c74be9ddac31398a57dde82986cadcc47b498ed780ffb2d750042e +size 6596012352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ae3216e --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: leafspark/Llama-3.1-8B-MultiReflection-Instruct +datasets: +- leafspark/DetailedReflection-Claude-v3_5-Sonnet +language: +- en +- de +- fr +- it +- pt +- hi +- es +- th +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- reflection +- unsloth +- peft +- llama +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/leafspark/Llama-3.1-8B-MultiReflection-Instruct + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-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-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-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-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-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-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-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-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.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-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.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-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-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-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-MultiReflection-Instruct-i1-GGUF/resolve/main/Llama-3.1-8B-MultiReflection-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..d68c956 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24b2573f17fd062126e59fa7f5ad03f1d69f96f3729aa67c20d2c5f27ca5b192 +size 4988157