commit 9039bc256c62b29177b2f1c9d3eb841d91609f82 Author: ModelHub XC Date: Fri Oct 16 19:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralGemma-2b-FT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e173515 --- /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 +NeuralGemma-2b-FT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralGemma-2b-FT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralGemma-2b-FT.IQ4_XS.gguf b/NeuralGemma-2b-FT.IQ4_XS.gguf new file mode 100644 index 0000000..a056b04 --- /dev/null +++ b/NeuralGemma-2b-FT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a10a51a6bec676540da4dc4c1210653ccbe0965d892dcd4d254d52d3c42f14b +size 1501218688 diff --git a/NeuralGemma-2b-FT.Q2_K.gguf b/NeuralGemma-2b-FT.Q2_K.gguf new file mode 100644 index 0000000..cb527ca --- /dev/null +++ b/NeuralGemma-2b-FT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a77c5dbab69d1bd6b520b8c8fdd26a15cbc82c1b5b35766e989a05f3ce4e36 +size 1157924736 diff --git a/NeuralGemma-2b-FT.Q3_K_L.gguf b/NeuralGemma-2b-FT.Q3_K_L.gguf new file mode 100644 index 0000000..20f32e8 --- /dev/null +++ b/NeuralGemma-2b-FT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:755a26405b46941f85fc1f90f3ed0bdd94f7473d7723b9116e39922a458678f9 +size 1465591680 diff --git a/NeuralGemma-2b-FT.Q3_K_M.gguf b/NeuralGemma-2b-FT.Q3_K_M.gguf new file mode 100644 index 0000000..e37429d --- /dev/null +++ b/NeuralGemma-2b-FT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b557fd087f45c10fd1a990e593f0127e919cefd0c6722694b54fd81e78e63b +size 1383802752 diff --git a/NeuralGemma-2b-FT.Q3_K_S.gguf b/NeuralGemma-2b-FT.Q3_K_S.gguf new file mode 100644 index 0000000..21498c4 --- /dev/null +++ b/NeuralGemma-2b-FT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d7e4e29b8fa331cd2b62221cf06dc6439c73b4cb1d01c63b23414b8d5f1eb1 +size 1287980928 diff --git a/NeuralGemma-2b-FT.Q4_K_M.gguf b/NeuralGemma-2b-FT.Q4_K_M.gguf new file mode 100644 index 0000000..8cb3562 --- /dev/null +++ b/NeuralGemma-2b-FT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a65a394d8328d591c92c5d09fdecc583c8900797c2b6317bc69242b4a3385065 +size 1630263168 diff --git a/NeuralGemma-2b-FT.Q4_K_S.gguf b/NeuralGemma-2b-FT.Q4_K_S.gguf new file mode 100644 index 0000000..9aa09f6 --- /dev/null +++ b/NeuralGemma-2b-FT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3254b96aca5bca0660eb6c1d12666cef121a1728c5e8a162da8e39053056d245 +size 1559840640 diff --git a/NeuralGemma-2b-FT.Q5_K_M.gguf b/NeuralGemma-2b-FT.Q5_K_M.gguf new file mode 100644 index 0000000..daa07f3 --- /dev/null +++ b/NeuralGemma-2b-FT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:487520c54007c293df84791766b0d306a65bc7d0f90d19d8c50c642ba548a246 +size 1839650688 diff --git a/NeuralGemma-2b-FT.Q5_K_S.gguf b/NeuralGemma-2b-FT.Q5_K_S.gguf new file mode 100644 index 0000000..5bb436f --- /dev/null +++ b/NeuralGemma-2b-FT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daeb1e3e85f3fe3cc9e1c2add9e03356c055abe8bf9ab21949f24b785baaf1e1 +size 1798915968 diff --git a/NeuralGemma-2b-FT.Q6_K.gguf b/NeuralGemma-2b-FT.Q6_K.gguf new file mode 100644 index 0000000..3bb14ea --- /dev/null +++ b/NeuralGemma-2b-FT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82318b83248c1962210eac6087552f8c40a5ee7dae2cc1448ff5dbbfd30c0a52 +size 2062124928 diff --git a/NeuralGemma-2b-FT.Q8_0.gguf b/NeuralGemma-2b-FT.Q8_0.gguf new file mode 100644 index 0000000..a0d5491 --- /dev/null +++ b/NeuralGemma-2b-FT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ed9adb27b2f2887f95337f4a520323e29f417c759539d1f4832d5e8af70087c +size 2669070208 diff --git a/NeuralGemma-2b-FT.f16.gguf b/NeuralGemma-2b-FT.f16.gguf new file mode 100644 index 0000000..119d153 --- /dev/null +++ b/NeuralGemma-2b-FT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed18d639f1e9c6db07895693e0118c48804947bd3dca10b363f6819fe04592b0 +size 5018535808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7129427 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: Kukedlc/NeuralGemma-2b-FT +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Kukedlc/NeuralGemma-2b-FT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NeuralGemma-2b-FT-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/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralGemma-2b-FT-GGUF/resolve/main/NeuralGemma-2b-FT.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. + +