From 6576821a94efce9388ff3b79eb8ba6be615f14d5 Mon Sep 17 00:00:00 2001 From: ai-modelscope Date: Sat, 27 Jul 2024 01:39:24 +0800 Subject: [PATCH] Upload gemma-2-9b-it-Q3_K_XL.gguf with huggingface_hub --- .gitattributes | 7 ++ .huggingface/download/README.md.lock | 0 .huggingface/download/README.md.metadata | 3 + .../download/gemma-2-9b-it-IQ2_M.gguf.lock | 0 .../gemma-2-9b-it-IQ2_M.gguf.metadata | 3 + .../download/gemma-2-9b-it-IQ2_S.gguf.lock | 0 .../gemma-2-9b-it-IQ2_S.gguf.metadata | 3 + .../download/gemma-2-9b-it-IQ2_XS.gguf.lock | 0 .../gemma-2-9b-it-IQ2_XS.gguf.metadata | 3 + .../download/gemma-2-9b-it-IQ3_M.gguf.lock | 0 .../gemma-2-9b-it-IQ3_M.gguf.metadata | 3 + .../download/gemma-2-9b-it-IQ3_XS.gguf.lock | 0 .../gemma-2-9b-it-IQ3_XS.gguf.metadata | 3 + .../download/gemma-2-9b-it-IQ3_XXS.gguf.lock | 0 .../gemma-2-9b-it-IQ3_XXS.gguf.metadata | 3 + .../download/gemma-2-9b-it-IQ4_XS.gguf.lock | 0 .../gemma-2-9b-it-IQ4_XS.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q2_K.gguf.lock | 0 .../download/gemma-2-9b-it-Q2_K.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q2_K_L.gguf.lock | 0 .../gemma-2-9b-it-Q2_K_L.gguf.metadata | 3 + .../gemma-2-9b-it-Q3_K_L-Q8.gguf.lock | 0 .../gemma-2-9b-it-Q3_K_L-Q8.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q3_K_L.gguf.lock | 0 .../gemma-2-9b-it-Q3_K_L.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q3_K_M.gguf.lock | 0 .../gemma-2-9b-it-Q3_K_M.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q3_K_S.gguf.lock | 0 .../gemma-2-9b-it-Q3_K_S.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q3_K_XL.gguf.lock | 0 .../gemma-2-9b-it-Q3_K_XL.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q4_K_L.gguf.lock | 0 .../gemma-2-9b-it-Q4_K_L.gguf.metadata | 3 + .../gemma-2-9b-it-Q4_K_M-fp16.gguf.lock | 0 .../gemma-2-9b-it-Q4_K_M-fp16.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q4_K_M.gguf.lock | 0 .../gemma-2-9b-it-Q4_K_M.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q4_K_S.gguf.lock | 0 .../gemma-2-9b-it-Q4_K_S.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q5_K_L.gguf.lock | 0 .../gemma-2-9b-it-Q5_K_L.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q5_K_M.gguf.lock | 0 .../gemma-2-9b-it-Q5_K_M.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q5_K_S.gguf.lock | 0 .../gemma-2-9b-it-Q5_K_S.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q6_K-Q8.gguf.lock | 0 .../gemma-2-9b-it-Q6_K-Q8.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q6_K-f32.gguf.lock | 0 .../gemma-2-9b-it-Q6_K-f32.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q6_K.gguf.lock | 0 .../download/gemma-2-9b-it-Q6_K.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q6_K_L.gguf.lock | 0 .../gemma-2-9b-it-Q6_K_L.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q8_0-f16.gguf.lock | 0 .../gemma-2-9b-it-Q8_0-f16.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q8_0.gguf.lock | 0 .../download/gemma-2-9b-it-Q8_0.gguf.metadata | 3 + .../download/gemma-2-9b-it-Q8_0_L.gguf.lock | 0 .../gemma-2-9b-it-Q8_0_L.gguf.metadata | 3 + .../download/gemma-2-9b-it-f32.gguf.lock | 0 .../download/gemma-2-9b-it-f32.gguf.metadata | 3 + .../download/gemma-2-9b-it.imatrix.lock | 0 .../download/gemma-2-9b-it.imatrix.metadata | 3 + README.md | 73 ++++++++++--------- gemma-2-9b-it-IQ2_M.gguf | 4 +- gemma-2-9b-it-IQ2_S.gguf | 4 +- gemma-2-9b-it-IQ2_XS.gguf | 4 +- gemma-2-9b-it-IQ3_M.gguf | 4 +- gemma-2-9b-it-IQ3_XS.gguf | 4 +- gemma-2-9b-it-IQ3_XXS.gguf | 4 +- gemma-2-9b-it-IQ4_XS.gguf | 4 +- gemma-2-9b-it-Q2_K.gguf | 4 +- gemma-2-9b-it-Q2_K_L.gguf | 3 + gemma-2-9b-it-Q3_K_L-Q8.gguf | 3 + gemma-2-9b-it-Q3_K_L.gguf | 4 +- gemma-2-9b-it-Q3_K_M.gguf | 4 +- gemma-2-9b-it-Q3_K_S.gguf | 4 +- gemma-2-9b-it-Q3_K_XL.gguf | 3 + gemma-2-9b-it-Q4_K_L.gguf | 4 +- gemma-2-9b-it-Q4_K_M-fp16.gguf | 3 + gemma-2-9b-it-Q4_K_M.gguf | 4 +- gemma-2-9b-it-Q4_K_S.gguf | 4 +- gemma-2-9b-it-Q5_K_L.gguf | 4 +- gemma-2-9b-it-Q5_K_M.gguf | 4 +- gemma-2-9b-it-Q5_K_S.gguf | 4 +- gemma-2-9b-it-Q6_K-Q8.gguf | 3 + gemma-2-9b-it-Q6_K-f32.gguf | 3 + gemma-2-9b-it-Q6_K.gguf | 4 +- gemma-2-9b-it-Q6_K_L.gguf | 4 +- gemma-2-9b-it-Q8_0-f16.gguf | 3 + gemma-2-9b-it-Q8_0.gguf | 4 +- gemma-2-9b-it-Q8_0_L.gguf | 4 +- gemma-2-9b-it-f32.gguf | 4 +- gemma-2-9b-it.imatrix | 4 +- 94 files changed, 207 insertions(+), 79 deletions(-) create mode 100644 .huggingface/download/README.md.lock create mode 100644 .huggingface/download/README.md.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-IQ2_M.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-IQ2_M.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-IQ2_S.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-IQ2_S.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-IQ2_XS.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-IQ2_XS.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-IQ3_M.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-IQ3_M.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-IQ3_XS.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-IQ3_XS.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-IQ3_XXS.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-IQ3_XXS.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-IQ4_XS.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-IQ4_XS.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q2_K.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q2_K.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q2_K_L.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q2_K_L.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q3_K_L-Q8.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q3_K_L-Q8.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q3_K_L.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q3_K_L.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q3_K_M.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q3_K_M.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q3_K_S.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q3_K_S.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q3_K_XL.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q3_K_XL.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q4_K_L.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q4_K_L.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q4_K_M-fp16.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q4_K_M-fp16.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q4_K_M.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q4_K_M.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q4_K_S.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q4_K_S.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q5_K_L.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q5_K_L.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q5_K_M.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q5_K_M.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q5_K_S.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q5_K_S.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q6_K-Q8.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q6_K-Q8.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q6_K-f32.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q6_K-f32.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q6_K.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q6_K.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q6_K_L.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q6_K_L.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q8_0-f16.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q8_0-f16.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q8_0.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q8_0.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-Q8_0_L.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-Q8_0_L.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it-f32.gguf.lock create mode 100644 .huggingface/download/gemma-2-9b-it-f32.gguf.metadata create mode 100644 .huggingface/download/gemma-2-9b-it.imatrix.lock create mode 100644 .huggingface/download/gemma-2-9b-it.imatrix.metadata create mode 100644 gemma-2-9b-it-Q2_K_L.gguf create mode 100644 gemma-2-9b-it-Q3_K_L-Q8.gguf create mode 100644 gemma-2-9b-it-Q3_K_XL.gguf create mode 100644 gemma-2-9b-it-Q4_K_M-fp16.gguf create mode 100644 gemma-2-9b-it-Q6_K-Q8.gguf create mode 100644 gemma-2-9b-it-Q6_K-f32.gguf create mode 100644 gemma-2-9b-it-Q8_0-f16.gguf diff --git a/.gitattributes b/.gitattributes index a8aaad7..787cce5 100644 --- a/.gitattributes +++ b/.gitattributes @@ -56,3 +56,10 @@ gemma-2-9b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text gemma-2-9b-it-Q8_0_L.gguf filter=lfs diff=lfs merge=lfs -text gemma-2-9b-it-f32.gguf filter=lfs diff=lfs merge=lfs -text gemma-2-9b-it.imatrix filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q6_K-Q8.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q6_K-f32.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q3_K_L-Q8.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q4_K_M-fp16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q8_0-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/.huggingface/download/README.md.lock b/.huggingface/download/README.md.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/README.md.metadata b/.huggingface/download/README.md.metadata new file mode 100644 index 0000000..b10aec2 --- /dev/null +++ b/.huggingface/download/README.md.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +cdc07b304b8c83da471390e12a15ca3a57aa0894 +1722008559.6692302 diff --git a/.huggingface/download/gemma-2-9b-it-IQ2_M.gguf.lock b/.huggingface/download/gemma-2-9b-it-IQ2_M.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-IQ2_M.gguf.metadata b/.huggingface/download/gemma-2-9b-it-IQ2_M.gguf.metadata new file mode 100644 index 0000000..28a2f25 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-IQ2_M.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +e152459c333bc687d3829e551e9c9c3f51abc087ba9f87d82033847e48db3df4 +1722008663.1916308 diff --git a/.huggingface/download/gemma-2-9b-it-IQ2_S.gguf.lock b/.huggingface/download/gemma-2-9b-it-IQ2_S.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-IQ2_S.gguf.metadata b/.huggingface/download/gemma-2-9b-it-IQ2_S.gguf.metadata new file mode 100644 index 0000000..d7fe6b4 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-IQ2_S.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +0725ca79e7415d9a23d0cdcd3f2376c1b989777dd07cd8c088af23bb4fc1fa28 +1722008663.2204618 diff --git a/.huggingface/download/gemma-2-9b-it-IQ2_XS.gguf.lock b/.huggingface/download/gemma-2-9b-it-IQ2_XS.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-IQ2_XS.gguf.metadata b/.huggingface/download/gemma-2-9b-it-IQ2_XS.gguf.metadata new file mode 100644 index 0000000..4bfbf46 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-IQ2_XS.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +010fb98c74fd5b413008adb14f62a0a6886883936dbc5693f45fd389b54bfd40 +1722008591.1106663 diff --git a/.huggingface/download/gemma-2-9b-it-IQ3_M.gguf.lock b/.huggingface/download/gemma-2-9b-it-IQ3_M.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-IQ3_M.gguf.metadata b/.huggingface/download/gemma-2-9b-it-IQ3_M.gguf.metadata new file mode 100644 index 0000000..3decdc6 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-IQ3_M.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +d117938c5ebd91f0cbe1962236d04b42a716b03ebf54560196773f51bd1b2acb +1722008663.217857 diff --git a/.huggingface/download/gemma-2-9b-it-IQ3_XS.gguf.lock b/.huggingface/download/gemma-2-9b-it-IQ3_XS.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-IQ3_XS.gguf.metadata b/.huggingface/download/gemma-2-9b-it-IQ3_XS.gguf.metadata new file mode 100644 index 0000000..6f397ab --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-IQ3_XS.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +379fb78fa6453222a54d85ed04cb376663ccc838347412eccab587290c8df1b9 +1722008663.261843 diff --git a/.huggingface/download/gemma-2-9b-it-IQ3_XXS.gguf.lock b/.huggingface/download/gemma-2-9b-it-IQ3_XXS.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-IQ3_XXS.gguf.metadata b/.huggingface/download/gemma-2-9b-it-IQ3_XXS.gguf.metadata new file mode 100644 index 0000000..35216ef --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-IQ3_XXS.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +8a57501217fee57586ec916fe196cce8e0f98d9a493eb817f3f27ea75b4904c9 +1722008663.2493024 diff --git a/.huggingface/download/gemma-2-9b-it-IQ4_XS.gguf.lock b/.huggingface/download/gemma-2-9b-it-IQ4_XS.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-IQ4_XS.gguf.metadata b/.huggingface/download/gemma-2-9b-it-IQ4_XS.gguf.metadata new file mode 100644 index 0000000..2d866d8 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-IQ4_XS.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +c79966f200495368e8d1d4fecefbfdd0176327ec76968522c6fe13c397ad5d58 +1722008663.2340443 diff --git a/.huggingface/download/gemma-2-9b-it-Q2_K.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q2_K.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q2_K.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q2_K.gguf.metadata new file mode 100644 index 0000000..a9edb35 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q2_K.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +2efce51c0d774a47c247c07ec6f109f670e3da4f4eec0f9322d72e3635622403 +1722008663.1963668 diff --git a/.huggingface/download/gemma-2-9b-it-Q2_K_L.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q2_K_L.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q2_K_L.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q2_K_L.gguf.metadata new file mode 100644 index 0000000..f358321 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q2_K_L.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +0c0c08d499a7a491f50bf68c6b925a27134a98f6a1fbcfbdeec558297884ea72 +1722008663.2521818 diff --git a/.huggingface/download/gemma-2-9b-it-Q3_K_L-Q8.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q3_K_L-Q8.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q3_K_L-Q8.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q3_K_L-Q8.gguf.metadata new file mode 100644 index 0000000..1383333 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q3_K_L-Q8.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +b8a45c72fee34ade31f7fcd2eec5e7eaafb51d7e1e80fe1762eff1a33e83d2fc +1722008778.1372104 diff --git a/.huggingface/download/gemma-2-9b-it-Q3_K_L.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q3_K_L.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q3_K_L.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q3_K_L.gguf.metadata new file mode 100644 index 0000000..bb853e9 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q3_K_L.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +38fbe0303ac54882c72fd28f636abf731e4bd813809c7a1cffc829980391bcb3 +1722008776.062595 diff --git a/.huggingface/download/gemma-2-9b-it-Q3_K_M.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q3_K_M.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q3_K_M.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q3_K_M.gguf.metadata new file mode 100644 index 0000000..410f7b8 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q3_K_M.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +3b5cb881500b1f72d456784a70214c8e49b7b3f49dae4fe524ca2c19e650b18b +1722008776.73387 diff --git a/.huggingface/download/gemma-2-9b-it-Q3_K_S.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q3_K_S.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q3_K_S.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q3_K_S.gguf.metadata new file mode 100644 index 0000000..33277dc --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q3_K_S.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +594a305f4806f982808a07e0271e6e9354e4557c2a1a72383005b41b200830d8 +1722008763.8150647 diff --git a/.huggingface/download/gemma-2-9b-it-Q3_K_XL.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q3_K_XL.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q3_K_XL.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q3_K_XL.gguf.metadata new file mode 100644 index 0000000..37c082e --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q3_K_XL.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +6609cc2ebba6311806ee84116af44e7fb26762f116572a8181aad4a5da5c9e95 +1722009026.903439 diff --git a/.huggingface/download/gemma-2-9b-it-Q4_K_L.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q4_K_L.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q4_K_L.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q4_K_L.gguf.metadata new file mode 100644 index 0000000..7731bba --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q4_K_L.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +ed8573f0d1e3ca58e471498fd162a65d4f4253dffdec28a7ba394fdcae92f1f3 +1722008778.7330132 diff --git a/.huggingface/download/gemma-2-9b-it-Q4_K_M-fp16.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q4_K_M-fp16.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q4_K_M-fp16.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q4_K_M-fp16.gguf.metadata new file mode 100644 index 0000000..a492711 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q4_K_M-fp16.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +0452e54ba9b6c5b2e466fbd7f28c089fefb7c3dceddcc2b75becab6b16cae523 +1722008794.5926306 diff --git a/.huggingface/download/gemma-2-9b-it-Q4_K_M.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q4_K_M.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q4_K_M.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q4_K_M.gguf.metadata new file mode 100644 index 0000000..d9a9a8d --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q4_K_M.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +13b2a7b4115bbd0900162edcebe476da1ba1fc24e718e8b40d32f6e300f56dfe +1722008777.381287 diff --git a/.huggingface/download/gemma-2-9b-it-Q4_K_S.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q4_K_S.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q4_K_S.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q4_K_S.gguf.metadata new file mode 100644 index 0000000..61c0f95 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q4_K_S.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +61fd8af95257d1e39fa3bab7f4e4f7af65812f4fe017a808913f3c1c7151d33a +1722008849.6402676 diff --git a/.huggingface/download/gemma-2-9b-it-Q5_K_L.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q5_K_L.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q5_K_L.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q5_K_L.gguf.metadata new file mode 100644 index 0000000..941487d --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q5_K_L.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +fcff2482f87cf4ba5bf0dca01cbde26abc9c77aa0caac0a792636219ce827e75 +1722008894.1712573 diff --git a/.huggingface/download/gemma-2-9b-it-Q5_K_M.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q5_K_M.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q5_K_M.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q5_K_M.gguf.metadata new file mode 100644 index 0000000..746e594 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q5_K_M.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +a4b0b55ce809a09baaefb789b0046ac77ecd502aba8aeb2ed63cc237d9f40ce7 +1722008894.2503803 diff --git a/.huggingface/download/gemma-2-9b-it-Q5_K_S.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q5_K_S.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q5_K_S.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q5_K_S.gguf.metadata new file mode 100644 index 0000000..5ea6415 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q5_K_S.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +ca83ab1d6a8df1f2b82ba2889dfeae77b878386ba60b8f55bad8cd370e2cc738 +1722008923.0811846 diff --git a/.huggingface/download/gemma-2-9b-it-Q6_K-Q8.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q6_K-Q8.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q6_K-Q8.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q6_K-Q8.gguf.metadata new file mode 100644 index 0000000..1466869 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q6_K-Q8.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +4e000b337787bd1cf2f07bbcf31709e6ff4fad7f383156741e674027d4038277 +1722008916.3342438 diff --git a/.huggingface/download/gemma-2-9b-it-Q6_K-f32.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q6_K-f32.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q6_K-f32.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q6_K-f32.gguf.metadata new file mode 100644 index 0000000..6d80cb5 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q6_K-f32.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +8b36d8f25b92b38a3c193f8e382f3df13699db42f65b124948db74b1f0a6b21b +1722008958.2288108 diff --git a/.huggingface/download/gemma-2-9b-it-Q6_K.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q6_K.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q6_K.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q6_K.gguf.metadata new file mode 100644 index 0000000..74e27b5 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q6_K.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +70ea6fe1a4a8005ef6a0b379a87d271028cfa1b0be5fa2848e30419653d717a4 +1722008913.8530598 diff --git a/.huggingface/download/gemma-2-9b-it-Q6_K_L.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q6_K_L.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q6_K_L.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q6_K_L.gguf.metadata new file mode 100644 index 0000000..777c700 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q6_K_L.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +497f1c006183cd186fb3503d90b80ba9a4518d8f6146a1f8e69615b20511c678 +1722009023.2152562 diff --git a/.huggingface/download/gemma-2-9b-it-Q8_0-f16.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q8_0-f16.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q8_0-f16.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q8_0-f16.gguf.metadata new file mode 100644 index 0000000..0c9a78d --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q8_0-f16.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +5f9cfe355265a0f78c4942e1a6cc6b7113ddb75748f7f1267490abfb34b0abc4 +1722009139.0869124 diff --git a/.huggingface/download/gemma-2-9b-it-Q8_0.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q8_0.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q8_0.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q8_0.gguf.metadata new file mode 100644 index 0000000..ab07641 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q8_0.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +07ac9ec01217d7bf2976a3a0dbf564a91b6957f94ab2ad30671eb6100f64bc2b +1722009029.678579 diff --git a/.huggingface/download/gemma-2-9b-it-Q8_0_L.gguf.lock b/.huggingface/download/gemma-2-9b-it-Q8_0_L.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-Q8_0_L.gguf.metadata b/.huggingface/download/gemma-2-9b-it-Q8_0_L.gguf.metadata new file mode 100644 index 0000000..daacb2d --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-Q8_0_L.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +e19cb326ba857bec47383ada7af3b0fd965605a44e0a3b6ab0b1e080a541597a +1722009120.7097569 diff --git a/.huggingface/download/gemma-2-9b-it-f32.gguf.lock b/.huggingface/download/gemma-2-9b-it-f32.gguf.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it-f32.gguf.metadata b/.huggingface/download/gemma-2-9b-it-f32.gguf.metadata new file mode 100644 index 0000000..3a03160 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it-f32.gguf.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +ac2d53301d4e91f0c3a1835df213af9334eaccb08be76afd694ec2101b57bdaa +1722010976.5704563 diff --git a/.huggingface/download/gemma-2-9b-it.imatrix.lock b/.huggingface/download/gemma-2-9b-it.imatrix.lock new file mode 100644 index 0000000..e69de29 diff --git a/.huggingface/download/gemma-2-9b-it.imatrix.metadata b/.huggingface/download/gemma-2-9b-it.imatrix.metadata new file mode 100644 index 0000000..00af695 --- /dev/null +++ b/.huggingface/download/gemma-2-9b-it.imatrix.metadata @@ -0,0 +1,3 @@ +d731033f3dc4018261fd39896e50984d398b4ac5 +40f30bcab948c839ffd9855c98ec76bffb7f5cae8d301d556ee8a96f5832058b +1722008927.2496314 diff --git a/README.md b/README.md index 8949a12..cdc07b3 100644 --- a/README.md +++ b/README.md @@ -1,22 +1,21 @@ --- -license: gemma +base_model: google/gemma-2-9b-it library_name: transformers +license: gemma pipeline_tag: text-generation -extra_gated_heading: Access Gemma on Hugging Face -extra_gated_prompt: >- - To access Gemma on Hugging Face, you’re required to review and agree to - Google’s usage license. To do this, please ensure you’re logged in to Hugging - Face and click below. Requests are processed immediately. -extra_gated_button_content: Acknowledge license tags: - conversational -- gemma2 quantized_by: bartowski +extra_gated_heading: Access Gemma on Hugging Face +extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and + agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging + Face and click below. Requests are processed immediately. +extra_gated_button_content: Acknowledge license --- ## Llamacpp imatrix Quantizations of gemma-2-9b-it -Using llama.cpp PR 8156 for quantization. +Using llama.cpp release b3389 for quantization. Original model: https://huggingface.co/google/gemma-2-9b-it @@ -25,9 +24,11 @@ All quants made using imatrix option with dataset from [here](https://gist.githu ## Prompt format ``` -user +user {prompt} model + +model ``` @@ -35,29 +36,34 @@ Note that this model does not support a System prompt. ## Download a file (not the whole branch) from below: -| Filename | Quant type | File Size | Description | -| -------- | ---------- | --------- | ----------- | -| [gemma-2-9b-it-Q8_0_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q8_1.gguf) | Q8_0_L | 10.68GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. | -| [gemma-2-9b-it-Q8_0.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q8_0.gguf) | Q8_0 | 9.82GB | Extremely high quality, generally unneeded but max available quant. | -| [gemma-2-9b-it-Q6_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q6_K_L.gguf) | Q6_K_L | 8.67GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. | -| [gemma-2-9b-it-Q6_K.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q6_K.gguf) | Q6_K | 7.58GB | Very high quality, near perfect, *recommended*. | -| [gemma-2-9b-it-Q5_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_L.gguf) | Q5_K_L | 7.73GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. | -| [gemma-2-9b-it-Q5_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_M.gguf) | Q5_K_M | 6.64GB | High quality, *recommended*. | -| [gemma-2-9b-it-Q5_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_S.gguf) | Q5_K_S | 6.48GB | High quality, *recommended*. | -| [gemma-2-9b-it-Q4_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_L.gguf) | Q4_K_L | 6.84GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, *recommended*. | -| [gemma-2-9b-it-Q4_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_M.gguf) | Q4_K_M | 5.76GB | Good quality, uses about 4.83 bits per weight, *recommended*. | -| [gemma-2-9b-it-Q4_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_S.gguf) | Q4_K_S | 5.47GB | Slightly lower quality with more space savings, *recommended*. | -| [gemma-2-9b-it-IQ4_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ4_XS.gguf) | IQ4_XS | 5.18GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | -| [gemma-2-9b-it-Q3_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_L.gguf) | Q3_K_L | 5.13GB | Lower quality but usable, good for low RAM availability. | -| [gemma-2-9b-it-Q3_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_M.gguf) | Q3_K_M | 4.76GB | Even lower quality. | -| [gemma-2-9b-it-IQ3_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_M.gguf) | IQ3_M | 4.49GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. | -| [gemma-2-9b-it-Q3_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_S.gguf) | Q3_K_S | 4.33GB | Low quality, not recommended. | -| [gemma-2-9b-it-IQ3_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_XS.gguf) | IQ3_XS | 4.14GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. | -| [gemma-2-9b-it-IQ3_XXS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_XXS.gguf) | IQ3_XXS | 3.79GB | Lower quality, new method with decent performance, comparable to Q3 quants. | -| [gemma-2-9b-it-Q2_K.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q2_K.gguf) | Q2_K | 3.80GB | Very low quality but surprisingly usable. | -| [gemma-2-9b-it-IQ2_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ2_M.gguf) | IQ2_M | 3.43GB | Very low quality, uses SOTA techniques to also be surprisingly usable. | -| [gemma-2-9b-it-IQ2_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ2_S.gguf) | IQ2_S | 3.21GB | Very low quality, uses SOTA techniques to be usable. | -| [gemma-2-9b-it-IQ2_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ2_XS.gguf) | IQ2_XS | 3.06GB | Very low quality, uses SOTA techniques to be usable. | +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [gemma-2-9b-it-f32.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-f32.gguf) | f32 | 36.97GB | false | Full F32 weights. | +| [gemma-2-9b-it-Q8_0.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q8_0.gguf) | Q8_0 | 9.83GB | false | Extremely high quality, generally unneeded but max available quant. | +| [gemma-2-9b-it-Q6_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q6_K_L.gguf) | Q6_K_L | 7.81GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [gemma-2-9b-it-Q6_K.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q6_K.gguf) | Q6_K | 7.59GB | false | Very high quality, near perfect, *recommended*. | +| [gemma-2-9b-it-Q5_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_L.gguf) | Q5_K_L | 6.87GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [gemma-2-9b-it-Q5_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_M.gguf) | Q5_K_M | 6.65GB | false | High quality, *recommended*. | +| [gemma-2-9b-it-Q5_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_S.gguf) | Q5_K_S | 6.48GB | false | High quality, *recommended*. | +| [gemma-2-9b-it-Q4_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_L.gguf) | Q4_K_L | 5.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [gemma-2-9b-it-Q4_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_M.gguf) | Q4_K_M | 5.76GB | false | Good quality, default size for must use cases, *recommended*. | +| [gemma-2-9b-it-Q4_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_S.gguf) | Q4_K_S | 5.48GB | false | Slightly lower quality with more space savings, *recommended*. | +| [gemma-2-9b-it-IQ4_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ4_XS.gguf) | IQ4_XS | 5.18GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [gemma-2-9b-it-Q3_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_L.gguf) | Q3_K_L | 5.13GB | false | Lower quality but usable, good for low RAM availability. | +| [gemma-2-9b-it-Q3_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_M.gguf) | Q3_K_M | 4.76GB | false | Low quality. | +| [gemma-2-9b-it-IQ3_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_M.gguf) | IQ3_M | 4.49GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [gemma-2-9b-it-Q3_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_S.gguf) | Q3_K_S | 4.34GB | false | Low quality, not recommended. | +| [gemma-2-9b-it-IQ3_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_XS.gguf) | IQ3_XS | 4.14GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [gemma-2-9b-it-Q2_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q2_K_L.gguf) | Q2_K_L | 4.03GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [gemma-2-9b-it-Q2_K.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q2_K.gguf) | Q2_K | 3.81GB | false | Very low quality but surprisingly usable. | +| [gemma-2-9b-it-IQ3_XXS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_XXS.gguf) | IQ3_XXS | 3.80GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [gemma-2-9b-it-IQ2_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ2_M.gguf) | IQ2_M | 3.43GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset + +Thank you ZeroWw for the inspiration to experiment with embed/output ## Downloading using huggingface-cli @@ -106,3 +112,4 @@ These I-quants can also be used on CPU and Apple Metal, but will be slower than The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm. Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski + diff --git a/gemma-2-9b-it-IQ2_M.gguf b/gemma-2-9b-it-IQ2_M.gguf index 9fcc0c2..77fd436 100644 --- a/gemma-2-9b-it-IQ2_M.gguf +++ b/gemma-2-9b-it-IQ2_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:94b6fe40ee612eb50159ad3e6fc97cc04c88ec7af8a813246d8d8c27c4522a00 -size 3434988384 +oid sha256:e152459c333bc687d3829e551e9c9c3f51abc087ba9f87d82033847e48db3df4 +size 3434668992 diff --git a/gemma-2-9b-it-IQ2_S.gguf b/gemma-2-9b-it-IQ2_S.gguf index 1b49e78..23f7d2a 100644 --- a/gemma-2-9b-it-IQ2_S.gguf +++ b/gemma-2-9b-it-IQ2_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ee80dfba6b4b7aee3528d742526d984496e621640d3c75eb521a36afed2c6010 -size 3211805536 +oid sha256:0725ca79e7415d9a23d0cdcd3f2376c1b989777dd07cd8c088af23bb4fc1fa28 +size 3211487104 diff --git a/gemma-2-9b-it-IQ2_XS.gguf b/gemma-2-9b-it-IQ2_XS.gguf index d042ed7..5fd3394 100644 --- a/gemma-2-9b-it-IQ2_XS.gguf +++ b/gemma-2-9b-it-IQ2_XS.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4f3ae196ff0f2a34927db3ed93451575394fb47e0a843f5d7915f2a9da02e7fd -size 3067700064 +oid sha256:010fb98c74fd5b413008adb14f62a0a6886883936dbc5693f45fd389b54bfd40 +size 3067381632 diff --git a/gemma-2-9b-it-IQ3_M.gguf b/gemma-2-9b-it-IQ3_M.gguf index cb64c4a..c646fc6 100644 --- a/gemma-2-9b-it-IQ3_M.gguf +++ b/gemma-2-9b-it-IQ3_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:744e3ead642fcbde768639cf2532f78da5b8ca80ce1718fed712c0ab38a5ebda -size 4494995808 +oid sha256:d117938c5ebd91f0cbe1962236d04b42a716b03ebf54560196773f51bd1b2acb +size 4494615488 diff --git a/gemma-2-9b-it-IQ3_XS.gguf b/gemma-2-9b-it-IQ3_XS.gguf index eb69568..eda7d27 100644 --- a/gemma-2-9b-it-IQ3_XS.gguf +++ b/gemma-2-9b-it-IQ3_XS.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:294638961d516cbc520c0dcd6a143fe0226f9969ee483e3e0d89b0f6f3587e4d -size 4145369440 +oid sha256:379fb78fa6453222a54d85ed04cb376663ccc838347412eccab587290c8df1b9 +size 4144989120 diff --git a/gemma-2-9b-it-IQ3_XXS.gguf b/gemma-2-9b-it-IQ3_XXS.gguf index 139d611..52e24d8 100644 --- a/gemma-2-9b-it-IQ3_XXS.gguf +++ b/gemma-2-9b-it-IQ3_XXS.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:79dfb350e10a4c7598b957c00381b7a8459f64e99457d4d05203dc2528683824 -size 3797058400 +oid sha256:8a57501217fee57586ec916fe196cce8e0f98d9a493eb817f3f27ea75b4904c9 +size 3796739008 diff --git a/gemma-2-9b-it-IQ4_XS.gguf b/gemma-2-9b-it-IQ4_XS.gguf index 9a58352..137e448 100644 --- a/gemma-2-9b-it-IQ4_XS.gguf +++ b/gemma-2-9b-it-IQ4_XS.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a8817cc2720f51f1130d994fcacd58b8860c88882d10bbffb29ed4b5f62f155b -size 5183410528 +oid sha256:c79966f200495368e8d1d4fecefbfdd0176327ec76968522c6fe13c397ad5d58 +size 5183030208 diff --git a/gemma-2-9b-it-Q2_K.gguf b/gemma-2-9b-it-Q2_K.gguf index 605dba6..c23e5d8 100644 --- a/gemma-2-9b-it-Q2_K.gguf +++ b/gemma-2-9b-it-Q2_K.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6c3d884107e4d01bac8316cbe755137beac8988cc9c8a9c8806b61f0c4d8bcc5 -size 3805778272 +oid sha256:2efce51c0d774a47c247c07ec6f109f670e3da4f4eec0f9322d72e3635622403 +size 3805397952 diff --git a/gemma-2-9b-it-Q2_K_L.gguf b/gemma-2-9b-it-Q2_K_L.gguf new file mode 100644 index 0000000..08518ae --- /dev/null +++ b/gemma-2-9b-it-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0c08d499a7a491f50bf68c6b925a27134a98f6a1fbcfbdeec558297884ea72 +size 4027605952 diff --git a/gemma-2-9b-it-Q3_K_L-Q8.gguf b/gemma-2-9b-it-Q3_K_L-Q8.gguf new file mode 100644 index 0000000..7d4e106 --- /dev/null +++ b/gemma-2-9b-it-Q3_K_L-Q8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a45c72fee34ade31f7fcd2eec5e7eaafb51d7e1e80fe1762eff1a33e83d2fc +size 5354661760 diff --git a/gemma-2-9b-it-Q3_K_L.gguf b/gemma-2-9b-it-Q3_K_L.gguf index 7d49534..a9d556b 100644 --- a/gemma-2-9b-it-Q3_K_L.gguf +++ b/gemma-2-9b-it-Q3_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d97e40aef60b072b15d9bdd41b171f141f46b45a18eaee257d9bf91daea52e1f -size 5132833120 +oid sha256:38fbe0303ac54882c72fd28f636abf731e4bd813809c7a1cffc829980391bcb3 +size 5132452800 diff --git a/gemma-2-9b-it-Q3_K_M.gguf b/gemma-2-9b-it-Q3_K_M.gguf index 2677797..e5b3452 100644 --- a/gemma-2-9b-it-Q3_K_M.gguf +++ b/gemma-2-9b-it-Q3_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:066d5cd0c5ad7a8d2b7407fb53f56858e6736c8248a06111b5f65afcbc709c8f -size 4762161504 +oid sha256:3b5cb881500b1f72d456784a70214c8e49b7b3f49dae4fe524ca2c19e650b18b +size 4761781184 diff --git a/gemma-2-9b-it-Q3_K_S.gguf b/gemma-2-9b-it-Q3_K_S.gguf index ab29bb4..322d0a0 100644 --- a/gemma-2-9b-it-Q3_K_S.gguf +++ b/gemma-2-9b-it-Q3_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6a0dc0e74df5cd76fb134249f4858bd4610049111482daa6dc1d8479ff283f21 -size 4338045280 +oid sha256:594a305f4806f982808a07e0271e6e9354e4557c2a1a72383005b41b200830d8 +size 4337664960 diff --git a/gemma-2-9b-it-Q3_K_XL.gguf b/gemma-2-9b-it-Q3_K_XL.gguf new file mode 100644 index 0000000..73b27a4 --- /dev/null +++ b/gemma-2-9b-it-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6609cc2ebba6311806ee84116af44e7fb26762f116572a8181aad4a5da5c9e95 +size 5354660768 diff --git a/gemma-2-9b-it-Q4_K_L.gguf b/gemma-2-9b-it-Q4_K_L.gguf index b2810f1..b1ce12c 100644 --- a/gemma-2-9b-it-Q4_K_L.gguf +++ b/gemma-2-9b-it-Q4_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:05dfbfc607fce0d039cac53098c387eb66c9c17587eb8bbf8b400c4769ae0252 -size 6844347232 +oid sha256:ed8573f0d1e3ca58e471498fd162a65d4f4253dffdec28a7ba394fdcae92f1f3 +size 5983265728 diff --git a/gemma-2-9b-it-Q4_K_M-fp16.gguf b/gemma-2-9b-it-Q4_K_M-fp16.gguf new file mode 100644 index 0000000..d46d2d2 --- /dev/null +++ b/gemma-2-9b-it-Q4_K_M-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0452e54ba9b6c5b2e466fbd7f28c089fefb7c3dceddcc2b75becab6b16cae523 +size 6843425696 diff --git a/gemma-2-9b-it-Q4_K_M.gguf b/gemma-2-9b-it-Q4_K_M.gguf index bddc5ab..da83fd7 100644 --- a/gemma-2-9b-it-Q4_K_M.gguf +++ b/gemma-2-9b-it-Q4_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0874bf61be2e4b3d0a4a75e58fbd442dc410745d513c1e1e5de0b54ae33e65db -size 5761438048 +oid sha256:13b2a7b4115bbd0900162edcebe476da1ba1fc24e718e8b40d32f6e300f56dfe +size 5761057728 diff --git a/gemma-2-9b-it-Q4_K_S.gguf b/gemma-2-9b-it-Q4_K_S.gguf index 9baec7e..e7257fb 100644 --- a/gemma-2-9b-it-Q4_K_S.gguf +++ b/gemma-2-9b-it-Q4_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2ae8828f11ad498fa6fb0c31ccbd5f6ec0bc3b579613f164b8bebc663f9d1763 -size 5479305568 +oid sha256:61fd8af95257d1e39fa3bab7f4e4f7af65812f4fe017a808913f3c1c7151d33a +size 5478925248 diff --git a/gemma-2-9b-it-Q5_K_L.gguf b/gemma-2-9b-it-Q5_K_L.gguf index c19a8a0..0d6b7dd 100644 --- a/gemma-2-9b-it-Q5_K_L.gguf +++ b/gemma-2-9b-it-Q5_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:381bc6455ee6bd33dfa3987d001678e390019e214a6f3e7fb17e22853a0102da -size 7730656096 +oid sha256:fcff2482f87cf4ba5bf0dca01cbde26abc9c77aa0caac0a792636219ce827e75 +size 6869574592 diff --git a/gemma-2-9b-it-Q5_K_M.gguf b/gemma-2-9b-it-Q5_K_M.gguf index 9432b06..a94d642 100644 --- a/gemma-2-9b-it-Q5_K_M.gguf +++ b/gemma-2-9b-it-Q5_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fd2ef3823778e3c138aebb5892fcc4587313549ec3c21b84103090ce4b7617b4 -size 6647746912 +oid sha256:a4b0b55ce809a09baaefb789b0046ac77ecd502aba8aeb2ed63cc237d9f40ce7 +size 6647366592 diff --git a/gemma-2-9b-it-Q5_K_S.gguf b/gemma-2-9b-it-Q5_K_S.gguf index 8dd3580..af6aa76 100644 --- a/gemma-2-9b-it-Q5_K_S.gguf +++ b/gemma-2-9b-it-Q5_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4ba2748d33407c999dc1c2fe6845e39eb686792cb5e42d5d1bc20599cfb2bdb7 -size 6483972448 +oid sha256:ca83ab1d6a8df1f2b82ba2889dfeae77b878386ba60b8f55bad8cd370e2cc738 +size 6483592128 diff --git a/gemma-2-9b-it-Q6_K-Q8.gguf b/gemma-2-9b-it-Q6_K-Q8.gguf new file mode 100644 index 0000000..c417ffa --- /dev/null +++ b/gemma-2-9b-it-Q6_K-Q8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e000b337787bd1cf2f07bbcf31709e6ff4fad7f383156741e674027d4038277 +size 7811278720 diff --git a/gemma-2-9b-it-Q6_K-f32.gguf b/gemma-2-9b-it-Q6_K-f32.gguf new file mode 100644 index 0000000..4face57 --- /dev/null +++ b/gemma-2-9b-it-Q6_K-f32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b36d8f25b92b38a3c193f8e382f3df13699db42f65b124948db74b1f0a6b21b +size 10506446720 diff --git a/gemma-2-9b-it-Q6_K.gguf b/gemma-2-9b-it-Q6_K.gguf index b745b5a..b414dc9 100644 --- a/gemma-2-9b-it-Q6_K.gguf +++ b/gemma-2-9b-it-Q6_K.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3f38ef3fe66173a34e05b7f356fa0880b3941e64c94618623f4c243e1a4fde12 -size 7589450080 +oid sha256:70ea6fe1a4a8005ef6a0b379a87d271028cfa1b0be5fa2848e30419653d717a4 +size 7589069760 diff --git a/gemma-2-9b-it-Q6_K_L.gguf b/gemma-2-9b-it-Q6_K_L.gguf index 7416854..e4c603e 100644 --- a/gemma-2-9b-it-Q6_K_L.gguf +++ b/gemma-2-9b-it-Q6_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d69cac05ff85f04207610e19def2e741d0fda43c19e0bf64cc7dfef9f005a2ef -size 8672359264 +oid sha256:497f1c006183cd186fb3503d90b80ba9a4518d8f6146a1f8e69615b20511c678 +size 7811277760 diff --git a/gemma-2-9b-it-Q8_0-f16.gguf b/gemma-2-9b-it-Q8_0-f16.gguf new file mode 100644 index 0000000..9357cd7 --- /dev/null +++ b/gemma-2-9b-it-Q8_0-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9cfe355265a0f78c4942e1a6cc6b7113ddb75748f7f1267490abfb34b0abc4 +size 10687308704 diff --git a/gemma-2-9b-it-Q8_0.gguf b/gemma-2-9b-it-Q8_0.gguf index e270b80..9c17e0f 100644 --- a/gemma-2-9b-it-Q8_0.gguf +++ b/gemma-2-9b-it-Q8_0.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:68ef14eb96fb6ab0dfb04dc9d73e4b5ff42fda0011110a160881d20b3d84b594 -size 9827640160 +oid sha256:07ac9ec01217d7bf2976a3a0dbf564a91b6957f94ab2ad30671eb6100f64bc2b +size 9827148736 diff --git a/gemma-2-9b-it-Q8_0_L.gguf b/gemma-2-9b-it-Q8_0_L.gguf index 754f558..f392175 100644 --- a/gemma-2-9b-it-Q8_0_L.gguf +++ b/gemma-2-9b-it-Q8_0_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0c2c8fe89751b1be794ce20ae92a764b3fe7fdfad735e5402650b5e40ad5788c -size 10688230240 +oid sha256:e19cb326ba857bec47383ada7af3b0fd965605a44e0a3b6ab0b1e080a541597a +size 10687309696 diff --git a/gemma-2-9b-it-f32.gguf b/gemma-2-9b-it-f32.gguf index 4630d8b..97b36af 100644 --- a/gemma-2-9b-it-f32.gguf +++ b/gemma-2-9b-it-f32.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4f7d9c68f33c338a0d98faf6bad67cb13d39a5d4f3c87965bff4d62620d27d70 -size 36974719488 +oid sha256:ac2d53301d4e91f0c3a1835df213af9334eaccb08be76afd694ec2101b57bdaa +size 36972880544 diff --git a/gemma-2-9b-it.imatrix b/gemma-2-9b-it.imatrix index c62773b..896565f 100644 --- a/gemma-2-9b-it.imatrix +++ b/gemma-2-9b-it.imatrix @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3ebc87750f8830146ae668032ca7e319bfbf89e4276c1a514aeee1be9e6addfd -size 6116901 +oid sha256:40f30bcab948c839ffd9855c98ec76bffb7f5cae8d301d556ee8a96f5832058b +size 6116900