commit d11f94364d315f82555467b07a453e6516fe3e61 Author: ModelHub XC Date: Mon Apr 27 11:16:30 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-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..59212d1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BgGPT-Gemma-2-9B-IT-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.IQ4_XS.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..5351730 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f9dc88df7f380b166909387892f9876f9176f52b515f49f58b46feee095351e +size 5223172096 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q2_K.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q2_K.gguf new file mode 100644 index 0000000..124476f --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d8d5fb64239866a82c4e2b2f6a43463477b02397924e5c1a4d31ba0dc831b14 +size 3805399040 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_L.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..1b0a217 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7635e2d8a507aeefe4720aac7a7d9d2891dd8a7345c0d58a76a3b52d2ee7626d +size 5132453888 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_M.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..2a44fd1 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c274e512ac94ece15c5550614b88e3c9bf755f321688ba79f9f535e31e7554 +size 4761782272 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_S.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..db75676 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d0f0e6d3ec89ba9dc663d5ff9ac699fac52217d7fd10654c1a4c8bb955ca0f5 +size 4337666048 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q4_0_4_4.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q4_0_4_4.gguf new file mode 100644 index 0000000..d439c77 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76811d5ac5531de2a69fe5a23e5a1cab9bd912ce70ad98cd7534ceb21863f24d +size 5443143680 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q4_K_M.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..2a17942 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1af97476b17db8bc0619496d02e9fce6a28a0cc3bb5fe533b6496e0b480540e +size 5761058816 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q4_K_S.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..bccb592 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8559030b00c041371d847852d2b6712cadff2224bc09bc5a0ac90339d6f23413 +size 5478926336 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q5_K_M.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..7dcfa65 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:263400beaec95562137ecb80e872a2e85ef86e7b424a53f51b344d088899320e +size 6647367680 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q5_K_S.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..74ca659 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e91dc883c4dc765a62645a352a4677d1f2ca3416a741da265c891e31ed2e75ee +size 6483593216 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q6_K.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q6_K.gguf new file mode 100644 index 0000000..38375fb --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a92e2160952ef789bdec4ecdc59b309b568632d952f1d1f632ad80287b01ef +size 7589070848 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.Q8_0.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.Q8_0.gguf new file mode 100644 index 0000000..0675c81 --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b275e9d8d3f6f9a9218abf2b6de7dfd7ee7dcd79cfc7070e891b3411e058202d +size 9827149824 diff --git a/BgGPT-Gemma-2-9B-IT-v1.0.f16.gguf b/BgGPT-Gemma-2-9B-IT-v1.0.f16.gguf new file mode 100644 index 0000000..a87f92f --- /dev/null +++ b/BgGPT-Gemma-2-9B-IT-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03bb8dac2ae8fcc220157b9ad47c847e404771f0fbc7bcbe1e6aed559425887e +size 18490681344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..461a756 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +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 + + + + + + +static quants of https://huggingface.co/INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-i1-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-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BgGPT-Gemma-2-9B-IT-v1.0-GGUF/resolve/main/BgGPT-Gemma-2-9B-IT-v1.0.f16.gguf) | f16 | 18.6 | 16 bpw, overkill | + +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. + +