commit d390fc17f20387eb31c6ae8507295a02d2be3d85 Author: ModelHub XC Date: Fri May 1 09:47:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gema4b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1d971f2 --- /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 +Gema4b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gema4b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gema4b.IQ4_XS.gguf b/Gema4b.IQ4_XS.gguf new file mode 100644 index 0000000..e0d6288 --- /dev/null +++ b/Gema4b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02c02f89e9c906225d509d9a2473a8b91e08c6f6b5540c0a82f5b928110f4dae +size 718168096 diff --git a/Gema4b.Q2_K.gguf b/Gema4b.Q2_K.gguf new file mode 100644 index 0000000..8fd9a52 --- /dev/null +++ b/Gema4b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d5d232c5fd1930b53024aa710a0f404b68b25ced8d5c32244b7e4b571275f9 +size 689815072 diff --git a/Gema4b.Q3_K_L.gguf b/Gema4b.Q3_K_L.gguf new file mode 100644 index 0000000..7dcc4de --- /dev/null +++ b/Gema4b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82ce95eb060abd19fb6cd3cb4d93539b0cd62617d21cba0ace8c4bf01f712eab +size 751576096 diff --git a/Gema4b.Q3_K_M.gguf b/Gema4b.Q3_K_M.gguf new file mode 100644 index 0000000..4714873 --- /dev/null +++ b/Gema4b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60731b11971c412e8899ca2a75461acd273ed79f72e0781bebe0cb6865c59ace +size 722416672 diff --git a/Gema4b.Q3_K_S.gguf b/Gema4b.Q3_K_S.gguf new file mode 100644 index 0000000..a62ff56 --- /dev/null +++ b/Gema4b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:638971d10e36790c0f0f5cacb9e77e3c95fb80c7344ecbbf0387ca0ec41491e9 +size 688856608 diff --git a/Gema4b.Q4_K_M.gguf b/Gema4b.Q4_K_M.gguf new file mode 100644 index 0000000..e11cbd6 --- /dev/null +++ b/Gema4b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94084aeda92acd79ea14a836634dd3bc25c1dc51bfb24e30d19d655cdf3f7bbd +size 806058784 diff --git a/Gema4b.Q4_K_S.gguf b/Gema4b.Q4_K_S.gguf new file mode 100644 index 0000000..d222256 --- /dev/null +++ b/Gema4b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2f2438fd04eba9d3c6fa9df98819e014acafe815cc66c495e15a2d8f10bad9 +size 780993568 diff --git a/Gema4b.Q5_K_M.gguf b/Gema4b.Q5_K_M.gguf new file mode 100644 index 0000000..b3fd237 --- /dev/null +++ b/Gema4b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deef7e7484dcedd1487dbe9bfb82605edaf55b585618447a8ec9e2cdb7d32fe9 +size 851346208 diff --git a/Gema4b.Q5_K_S.gguf b/Gema4b.Q5_K_S.gguf new file mode 100644 index 0000000..36893b1 --- /dev/null +++ b/Gema4b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:127e8b983a1796f6af3e1543f72e85a0f47b1a5a577981e8dbe05ddfc90f5c91 +size 836400160 diff --git a/Gema4b.Q6_K.gguf b/Gema4b.Q6_K.gguf new file mode 100644 index 0000000..f32869f --- /dev/null +++ b/Gema4b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84419a01e10cc95a430de8055061bf2a2b8311500f4f2b4e868de3f9203498c3 +size 1011739168 diff --git a/Gema4b.Q8_0.gguf b/Gema4b.Q8_0.gguf new file mode 100644 index 0000000..d7cad7d --- /dev/null +++ b/Gema4b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b7e4e7bed3964b6d1d76739b7e743aa0130cfe2756a64dab53f583368fe9560 +size 1069306912 diff --git a/Gema4b.f16.gguf b/Gema4b.f16.gguf new file mode 100644 index 0000000..fc6cded --- /dev/null +++ b/Gema4b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0575c42274df6f3af2e850f5cde99aaff3878f9fc3633bba62f3672757b85bd +size 2006574112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1f325f0 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Alamaks/Gema4b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3_text +--- +## About + + + + + + +static quants of https://huggingface.co/Alamaks/Gema4b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gema4b-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Gema4b-GGUF/resolve/main/Gema4b.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.Q8_0.gguf) | Q8_0 | 1.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gema4b-GGUF/resolve/main/Gema4b.f16.gguf) | f16 | 2.1 | 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. + +