commit 520e85eb414cddb380ec74f8df9cc571d4e3cb48 Author: ModelHub XC Date: Sat May 9 20:27:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..719b1e8 --- /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 +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ1_M.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ1_M.gguf new file mode 100644 index 0000000..9a5bd58 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a02663d6c5d2b267565b5f73b14452f613d2187bfe1d15943e76d083b3e58ee +size 2545952992 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ1_S.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ1_S.gguf new file mode 100644 index 0000000..798a8b6 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:956ccb70f48fe2af888105930eafabfb152a17645d2641493328af2cf4dc9ea2 +size 2378565856 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_M.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_M.gguf new file mode 100644 index 0000000..d8538be --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef9944f9635193bbe54ec5f59a0fe0cb380e66415d4d4fed2c5dc8f7b27f41ad +size 3434670304 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_S.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_S.gguf new file mode 100644 index 0000000..8ea710b --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2763fceea48bba790397d119e77f78600d2aefb26e77575daf4912c95c6ed631 +size 3211487456 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_XS.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4fea746 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97f86155a5a77f9f3c6db7323b3a56a8417eead44dc9b41d85f3480483a6612 +size 3067381984 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_XXS.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..b8ba96e --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1291ee230d6770c9597e88a6d3611ceb37eea38051f6f508e29c71cf64f78e26 +size 2824931552 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_M.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_M.gguf new file mode 100644 index 0000000..294afd4 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d35f0431ab3ac8483614701d3e176a5f22698da381c6ec972c2bb88c2d964d28 +size 4494616800 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_S.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_S.gguf new file mode 100644 index 0000000..7e384b8 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8a47e08c20ad1206c8dd40a61b61ac01cfc0798b967ecd450faef5de7bf1a28 +size 4337666272 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_XS.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4ce43e0 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40afd7244b8056d4983466db089b411b7de35945af619f2b600db35b72720a8f +size 4144990432 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_XXS.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..03e09c7 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1bfa80768a347888cd51c14f289931f5cd4fa12f30d7e32b8da32801d7ed95a +size 3796740320 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ4_XS.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ4_XS.gguf new file mode 100644 index 0000000..06cc411 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419fa99cc7b11c6089800e42eb8ef2a98742455651dd466a01c3c2354f935e5d +size 5183031520 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q2_K.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q2_K.gguf new file mode 100644 index 0000000..2c804d7 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ac8068000b88a944865e95384226c402975778f6d43916dc03019159c66428a +size 3805399264 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_L.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_L.gguf new file mode 100644 index 0000000..87ed8f5 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32f8f2a1da3653a126a14b28742c649fee5cc2d23fb2c80c029b41504b12d23 +size 5132454112 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_M.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_M.gguf new file mode 100644 index 0000000..9242e2b --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16aa2aa81a3228d7d9d75d412f53a2ed711b69be2afd93aaadf21fe2bcae26b2 +size 4761782496 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_S.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ae63bc0 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a55415eaa9768a21babd76e5b6fe33f8f22a45d14a4b94edf505bdf1ced6dd +size 4337666272 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0.gguf new file mode 100644 index 0000000..a7a5fc5 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba19cc10ba82ab93f9371a1c798dffd3a8787d7d57f2bdfb9b5c20759d49d44 +size 5459200224 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_4_4.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..ff1ff1a --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ef404be1ad0b3fe20f856ee5669fdd93ce9e8f4942494f54a31fb8ce26d3273 +size 5443143904 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_4_8.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..69c558a --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f882a6088b2ac8ef344dd12e08fef3e14e1a59a4b4818199d2036734cd545f1b +size 5443143904 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_8_8.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..3906d6a --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87948df7ec3efbba3487bea7bc09e4c07a0b67ab05781b738cc3edb6e23abd3 +size 5443143904 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_K_M.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c753dd4 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1352d12ec4e5ec2f00a655c07d35aa84d635e600cba0a6c69f4c81b4507c3ce3 +size 5761059040 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_K_S.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_K_S.gguf new file mode 100644 index 0000000..496d728 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110dbaaa533cfa6f141aa1e7c6ff95f937412b30f6b41863cbb2bfcf94bad441 +size 5478926560 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q5_K_M.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q5_K_M.gguf new file mode 100644 index 0000000..654c04c --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a1eb7a8dcd1ff3d961b7a11b2520dcede4205842c6bcad1444dc5825a8a02ed +size 6647367904 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q5_K_S.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5468b7b --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378b94ff5e4ba223e8eb35dfb0be2d4829ab74ca92f89a6243ef3745a34ddc6a +size 6483593440 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q6_K.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q6_K.gguf new file mode 100644 index 0000000..3838d99 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37d6329b2d75d9a90e33a8ef7d6580b87b6f3f603ddbc48dee8407a6a02111dd +size 7589071072 diff --git a/README.md b/README.md new file mode 100644 index 0000000..33a9d4c --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0 +language: +- bg +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +tags: +- gemma2 +- instruct +- bggpt +- insait +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0 + + +static quants are available at https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-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/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 2.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ2_M.gguf) | i1-IQ2_M | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 5.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 5.5 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 5.5 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | 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..17bd8f0 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd72f374b21d5a9d5a2b446fff13ba0548d5f0c17e87faab0a6243ca126b15f7 +size 6116887