commit 64eadb4d20639dcbdf46cc5bb982651423b5fdeb Author: ModelHub XC Date: Thu Jul 16 16:47:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-2b-chat-doctor1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f9c198a --- /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-2b-chat-doctor1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2b-chat-doctor1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4a63e3d --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: JC-24/gemma-2b-chat-doctor1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/JC-24/gemma-2b-chat-doctor1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-2b-chat-doctor1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-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-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2b-chat-doctor1-GGUF/resolve/main/gemma-2b-chat-doctor1.f16.gguf) | f16 | 5.1 | 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. + + diff --git a/gemma-2b-chat-doctor1.IQ4_XS.gguf b/gemma-2b-chat-doctor1.IQ4_XS.gguf new file mode 100644 index 0000000..4a3c9e3 --- /dev/null +++ b/gemma-2b-chat-doctor1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3280e488dfcc8493157b95df002ebb0c802a950fd522d931f491b9f0674e2b7c +size 1501218656 diff --git a/gemma-2b-chat-doctor1.Q2_K.gguf b/gemma-2b-chat-doctor1.Q2_K.gguf new file mode 100644 index 0000000..9597a7c --- /dev/null +++ b/gemma-2b-chat-doctor1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb571ec9e3be0778672eae3c76d7dd310747ba0f44a800d6cc7c8a6bb40c5cf7 +size 1157924704 diff --git a/gemma-2b-chat-doctor1.Q3_K_L.gguf b/gemma-2b-chat-doctor1.Q3_K_L.gguf new file mode 100644 index 0000000..8186fca --- /dev/null +++ b/gemma-2b-chat-doctor1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44c06022e5bdc4906e776bb803dbe00445b5b70a62473b50a90b64a973525854 +size 1465591648 diff --git a/gemma-2b-chat-doctor1.Q3_K_M.gguf b/gemma-2b-chat-doctor1.Q3_K_M.gguf new file mode 100644 index 0000000..b9df2f8 --- /dev/null +++ b/gemma-2b-chat-doctor1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce064e285bbdb281720af3f090658a9de606c1e15e51faf634ea01af84825ac7 +size 1383802720 diff --git a/gemma-2b-chat-doctor1.Q3_K_S.gguf b/gemma-2b-chat-doctor1.Q3_K_S.gguf new file mode 100644 index 0000000..fbf9ef8 --- /dev/null +++ b/gemma-2b-chat-doctor1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d21ed886af73716076ccde09ada36a3f91aa6e5f0adabbcf084b0777165aa0 +size 1287980896 diff --git a/gemma-2b-chat-doctor1.Q4_K_M.gguf b/gemma-2b-chat-doctor1.Q4_K_M.gguf new file mode 100644 index 0000000..a24211c --- /dev/null +++ b/gemma-2b-chat-doctor1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f030c8de03d585d3a21e62f3ec12d7547e347bb9a49e6fc640bf70a07f5daa54 +size 1630263136 diff --git a/gemma-2b-chat-doctor1.Q4_K_S.gguf b/gemma-2b-chat-doctor1.Q4_K_S.gguf new file mode 100644 index 0000000..0f3caf6 --- /dev/null +++ b/gemma-2b-chat-doctor1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:471cfdc44d12ad642b33122cfa5b56ec75ce6f66d848a215f5d920b63bdfd1ca +size 1559840608 diff --git a/gemma-2b-chat-doctor1.Q5_K_M.gguf b/gemma-2b-chat-doctor1.Q5_K_M.gguf new file mode 100644 index 0000000..5dbb243 --- /dev/null +++ b/gemma-2b-chat-doctor1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc4884576cb0d8fc4bbd650a16150c9edb50d51dc315a229eadf252b369b5b61 +size 1839650656 diff --git a/gemma-2b-chat-doctor1.Q5_K_S.gguf b/gemma-2b-chat-doctor1.Q5_K_S.gguf new file mode 100644 index 0000000..d9b5e6f --- /dev/null +++ b/gemma-2b-chat-doctor1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:745e949fd8ac9d57b630042e5a9e3bdc2021c84bf9187f4f497498bb24b8484f +size 1798915936 diff --git a/gemma-2b-chat-doctor1.Q6_K.gguf b/gemma-2b-chat-doctor1.Q6_K.gguf new file mode 100644 index 0000000..75c1f50 --- /dev/null +++ b/gemma-2b-chat-doctor1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e5a104a8cb5f02d6b1a904a09915b069456bcc9200bb35a5f791a21406dfb2 +size 2062124896 diff --git a/gemma-2b-chat-doctor1.Q8_0.gguf b/gemma-2b-chat-doctor1.Q8_0.gguf new file mode 100644 index 0000000..6c4aecc --- /dev/null +++ b/gemma-2b-chat-doctor1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7823ce9b43daea4dad704a309033829e06bda2809582cc16967a3ec40fd16c9e +size 2669070176 diff --git a/gemma-2b-chat-doctor1.f16.gguf b/gemma-2b-chat-doctor1.f16.gguf new file mode 100644 index 0000000..c33f45e --- /dev/null +++ b/gemma-2b-chat-doctor1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a087f268478ba8bc762708d1c685bbcd254cff7efa1d8f0dfda08425839d46a +size 5018535776