commit 9dd5dbd03d73e3f40be4a885e2cee008d0e321f4 Author: ModelHub XC Date: Sat Jun 13 09:10:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8f83fbe --- /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 +none_quantization_medical_Gemma-1.1-7B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +none_quantization_medical_Gemma-1.1-7B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8dbb608 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: qsy71/none_quantization_medical_Gemma-1.1-7B-Chat +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/qsy71/none_quantization_medical_Gemma-1.1-7B-Chat + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#none_quantization_medical_Gemma-1.1-7B-Chat-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-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/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.Q2_K.gguf) | Q2_K | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_S.gguf) | Q3_K_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.Q5_K_S.gguf) | Q5_K_S | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/none_quantization_medical_Gemma-1.1-7B-Chat-GGUF/resolve/main/none_quantization_medical_Gemma-1.1-7B-Chat.f16.gguf) | f16 | 17.2 | 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/none_quantization_medical_Gemma-1.1-7B-Chat.IQ4_XS.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..590f281 --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b8c6f6277bfd24549771ede1cc045fd7d71c1d961a1eb8d0cb69b94a50f682 +size 4805012224 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.Q2_K.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.Q2_K.gguf new file mode 100644 index 0000000..c9cb517 --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523db132cfd495cf4e075d758610e611718226db12b10846d1b2fd8ce07e4b4e +size 3481447168 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_L.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..3710c00 --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:763347975e0d4c22ca436b024daa2606022c26c37b58e62da778d4cd0081910d +size 4709067520 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_M.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..5de7bae --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:261b8e034682398359f72e3c4d18715acda683b2a1f24b37db0d051622b57ff5 +size 4369328896 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_S.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..5d4bfff --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc62ee356a6a35e17edf6bd0a4cb767643fd6a4ac137caac32f6c2bd5992d9fc +size 3982404352 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.Q4_K_M.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..d293faf --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ccb4b58c128574cc6250fe06b557f5447f2453d47cc9de3bc408e51b3897d1f +size 5329758976 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.Q4_K_S.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..cfb6645 --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f0502ed00b74eae07da9c36e7d034c184e978ccaa62fd93073bfb559551ac2 +size 5046446848 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.Q5_K_M.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..57da85a --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11d955d9c2f9c40c75b6ed5090aeb02689e9c21c96094cce91952eb01619bd06 +size 6144502528 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.Q5_K_S.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..d1e1a0a --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0098a9aa99eb0120e8aaa29f1272102f639f2e58610b54b436e85da254883323 +size 5980728064 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.Q6_K.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.Q6_K.gguf new file mode 100644 index 0000000..26c905d --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d598a826f7a39d4f3f6d5703412b933505efb05c85ecc229bc27a11fd0a2215 +size 7010167552 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.Q8_0.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.Q8_0.gguf new file mode 100644 index 0000000..9cf3b3d --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83d19a44c634d9275d14b5caaa6c7322c60bdf722c701ab42365c4206498962d +size 9077844736 diff --git a/none_quantization_medical_Gemma-1.1-7B-Chat.f16.gguf b/none_quantization_medical_Gemma-1.1-7B-Chat.f16.gguf new file mode 100644 index 0000000..3538447 --- /dev/null +++ b/none_quantization_medical_Gemma-1.1-7B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e00bf49a11ab6297054617aa972678a2e5d71e1f9438f97f8d964a1a38a1d41d +size 17081756416