commit f1a28fb7b5b0e656ac93034e1597a12665556965 Author: ModelHub XC Date: Mon Jun 15 10:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b4ff4d5 --- /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 +gemma2-9b-cpt-sahabatai-v1-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-9b-cpt-sahabatai-v1-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b3aee9d --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct +language: +- en +- id +- jv +- su +library_name: transformers +license: gemma +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-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/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma2-9b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/gemma2-9b-cpt-sahabatai-v1-instruct.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. 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/gemma2-9b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..78c0e60 --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b557fdd7004f0f181e362b02752a8eeecf17960981e7750a51ca6f8af8ffce6 +size 5223171968 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q2_K.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q2_K.gguf new file mode 100644 index 0000000..5eedc03 --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717e5262c959a456f3ae2a09991d55fdbc7c6243833d85b9c9045c572278409c +size 3805398912 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..9faa2f4 --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a13005d54637f6171c6277997214bb9e27c1221c6dd9ed1a2a56c860abfd8a34 +size 5132453760 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..f1008b1 --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdba300294778c70946737c40cca42f76bd6cd9fa48b9681ad7b7e7f22429f0a +size 4761782144 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..73908c2 --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33dabe132cbd13033154351e96ac363b931d4f51fca1298f85e785e081f8d28f +size 4337665920 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_0_4_4.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..cbfcbba --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:868bef405af4242be8a1955d7ef59cdf7caaf84071b9d10c508079dad52393c4 +size 5443143552 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..84cdbe3 --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed6b468f9e121aa8349bbbdebc39aca38108f80e656d54eafa151a77dd2b3c0 +size 5761058688 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..683bd3f --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8ce195c0a331362aa63540c33c0434ef033850f2028ed5a972644aae92a0f42 +size 5478926208 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..3a0179e --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8bc63682adc91f5b62a5239355d415f8ce27cbdb0d7d0b626a1194b0a0c7db +size 6647367552 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..4e28c8b --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56386549a014dfab117cc198c3d877e35d519ad4060fdca1771bcb03ff29c3e9 +size 6483593088 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q6_K.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q6_K.gguf new file mode 100644 index 0000000..a733719 --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7744a236506b972f1e571a9321c09e74c509dbb6b9a4400994591e8e51416f94 +size 7589070720 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.Q8_0.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.Q8_0.gguf new file mode 100644 index 0000000..4af2dc0 --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5339a3c01000b5516a9e978052e155e858cf0c07a8763f2ab8291ac1f952d91 +size 9827149696 diff --git a/gemma2-9b-cpt-sahabatai-v1-instruct.f16.gguf b/gemma2-9b-cpt-sahabatai-v1-instruct.f16.gguf new file mode 100644 index 0000000..0f9ebad --- /dev/null +++ b/gemma2-9b-cpt-sahabatai-v1-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f14798fdaaa231131b68d202b366b64ac95c94990fa02d17ef1da403d7ea5e8e +size 18490681216