commit f7a3fede5f9f84900f6b474b912e716015c47434 Author: ModelHub XC Date: Sat Jun 13 08:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma-2-9b-medical-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f4206d2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Gemma-2-9b-medical.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.f16.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9b-medical.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma-2-9b-medical.IQ4_XS.gguf b/Gemma-2-9b-medical.IQ4_XS.gguf new file mode 100644 index 0000000..6e3d5ee --- /dev/null +++ b/Gemma-2-9b-medical.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c30261c3b632028860642d4fdb74116c07c7e10585a51bf3cbf3308c545fccd +size 5223170752 diff --git a/Gemma-2-9b-medical.Q2_K.gguf b/Gemma-2-9b-medical.Q2_K.gguf new file mode 100644 index 0000000..d92b6ac --- /dev/null +++ b/Gemma-2-9b-medical.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41db1662991034e06aab8403b8b323559994b5d688f3e4b06dcae9b38cd09505 +size 3805397696 diff --git a/Gemma-2-9b-medical.Q3_K_L.gguf b/Gemma-2-9b-medical.Q3_K_L.gguf new file mode 100644 index 0000000..c1ebc65 --- /dev/null +++ b/Gemma-2-9b-medical.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d12e9c26ac248cbec97b69d52d9cafad441722122793de5b5d36fc96708e0066 +size 5132452544 diff --git a/Gemma-2-9b-medical.Q3_K_M.gguf b/Gemma-2-9b-medical.Q3_K_M.gguf new file mode 100644 index 0000000..1bca018 --- /dev/null +++ b/Gemma-2-9b-medical.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:649da75139cabbffd20eca11a814b34172ccabb99f434e933e084f86a8aef2ff +size 4761780928 diff --git a/Gemma-2-9b-medical.Q3_K_S.gguf b/Gemma-2-9b-medical.Q3_K_S.gguf new file mode 100644 index 0000000..f1f575a --- /dev/null +++ b/Gemma-2-9b-medical.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1baf3c793c7aa2c43ba7695553130d0267fc2d33ccbe63f90bc934ee298f8b9c +size 4337664704 diff --git a/Gemma-2-9b-medical.Q4_K_M.gguf b/Gemma-2-9b-medical.Q4_K_M.gguf new file mode 100644 index 0000000..e1ec4c2 --- /dev/null +++ b/Gemma-2-9b-medical.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20b36129440b4a6577904f14a84a854863d37f4533d4a72607d0b2de1e7957c6 +size 5761057472 diff --git a/Gemma-2-9b-medical.Q4_K_S.gguf b/Gemma-2-9b-medical.Q4_K_S.gguf new file mode 100644 index 0000000..3ad6ec2 --- /dev/null +++ b/Gemma-2-9b-medical.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e90decdc33b86e0b11ff9a020ac3759f7df6eeccacc6832e5799e1fa6840816c +size 5478924992 diff --git a/Gemma-2-9b-medical.Q5_K_M.gguf b/Gemma-2-9b-medical.Q5_K_M.gguf new file mode 100644 index 0000000..75f68a3 --- /dev/null +++ b/Gemma-2-9b-medical.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b1a04420053ef1cb87845cbae053c0c1d159e31406b9e59e3555979568e41aa +size 6647366336 diff --git a/Gemma-2-9b-medical.Q5_K_S.gguf b/Gemma-2-9b-medical.Q5_K_S.gguf new file mode 100644 index 0000000..2104389 --- /dev/null +++ b/Gemma-2-9b-medical.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e50f5a885f6706b407d3f371c58d81ec536ddb297ae1d9031588b2cc6588516e +size 6483591872 diff --git a/Gemma-2-9b-medical.Q6_K.gguf b/Gemma-2-9b-medical.Q6_K.gguf new file mode 100644 index 0000000..d5b82f6 --- /dev/null +++ b/Gemma-2-9b-medical.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96ee09295a9b706562d6d033cd0402e60b6d3977045e5f6b9aa310523452cba1 +size 7589069504 diff --git a/Gemma-2-9b-medical.Q8_0.gguf b/Gemma-2-9b-medical.Q8_0.gguf new file mode 100644 index 0000000..233c084 --- /dev/null +++ b/Gemma-2-9b-medical.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b51152c23443f0ce4664a70033d27c756ef3b3940334386cf3d0e502a6986e +size 9827148480 diff --git a/Gemma-2-9b-medical.f16.gguf b/Gemma-2-9b-medical.f16.gguf new file mode 100644 index 0000000..356dec4 --- /dev/null +++ b/Gemma-2-9b-medical.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d94d5ca7d5057be5b713f98358497ff7ea1ec4ce302c6974f7b8cd42fc2347 +size 18490680000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..448ef9a --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: YiDuo1999/Gemma-2-9b-medical +language: +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/YiDuo1999/Gemma-2-9b-medical + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Gemma-2-9b-medical-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/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9b-medical-GGUF/resolve/main/Gemma-2-9b-medical.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. + +