commit 4aed09b146f3326ea4d1b9b421f05b1b86969f02 Author: ModelHub XC Date: Wed Jul 1 18:56:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma-2B-Alpaca-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bfc3716 --- /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-Alpaca.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.f16.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2B-Alpaca.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma-2B-Alpaca.IQ4_XS.gguf b/Gemma-2B-Alpaca.IQ4_XS.gguf new file mode 100644 index 0000000..9985d22 --- /dev/null +++ b/Gemma-2B-Alpaca.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b028519813eba1cd26070a90d1f81d57a7fe58965cb1f56d27580f7c2f35c505 +size 1501218688 diff --git a/Gemma-2B-Alpaca.Q2_K.gguf b/Gemma-2B-Alpaca.Q2_K.gguf new file mode 100644 index 0000000..34be2d4 --- /dev/null +++ b/Gemma-2B-Alpaca.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e131e51916065fd9e36d5ecccbf8e9363e8b4912ae7980011e6d55d9a77b4f20 +size 1157924736 diff --git a/Gemma-2B-Alpaca.Q3_K_L.gguf b/Gemma-2B-Alpaca.Q3_K_L.gguf new file mode 100644 index 0000000..91d99c3 --- /dev/null +++ b/Gemma-2B-Alpaca.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7505f18804f44b6c632ff864b1e906043bce52edbff02744072ce4fb11f43317 +size 1465591680 diff --git a/Gemma-2B-Alpaca.Q3_K_M.gguf b/Gemma-2B-Alpaca.Q3_K_M.gguf new file mode 100644 index 0000000..99cb866 --- /dev/null +++ b/Gemma-2B-Alpaca.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c761ae962d3ca1a64122586908507d3952ee9fc48e971565162e99aab64f77ce +size 1383802752 diff --git a/Gemma-2B-Alpaca.Q3_K_S.gguf b/Gemma-2B-Alpaca.Q3_K_S.gguf new file mode 100644 index 0000000..201b96b --- /dev/null +++ b/Gemma-2B-Alpaca.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b4ffb36c38d20eb4909ee65b3629678f9cd1515548eb4f8ddfe9c68838aec30 +size 1287980928 diff --git a/Gemma-2B-Alpaca.Q4_K_M.gguf b/Gemma-2B-Alpaca.Q4_K_M.gguf new file mode 100644 index 0000000..8900fc2 --- /dev/null +++ b/Gemma-2B-Alpaca.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8d5c066fbf5fe8ea615bd111da618f36b6d006bcf67f94926c2aa402ab8f535 +size 1630263168 diff --git a/Gemma-2B-Alpaca.Q4_K_S.gguf b/Gemma-2B-Alpaca.Q4_K_S.gguf new file mode 100644 index 0000000..bbc88e6 --- /dev/null +++ b/Gemma-2B-Alpaca.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58f6653e3648399ca6204414bd1730cb2e19648b01a272f58f75802fe1596fa9 +size 1559840640 diff --git a/Gemma-2B-Alpaca.Q5_K_M.gguf b/Gemma-2B-Alpaca.Q5_K_M.gguf new file mode 100644 index 0000000..ed7849d --- /dev/null +++ b/Gemma-2B-Alpaca.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec64845f1fbb16581adcece72478862a20acfed2e557ce2b7fcdec7071a4241a +size 1839650688 diff --git a/Gemma-2B-Alpaca.Q5_K_S.gguf b/Gemma-2B-Alpaca.Q5_K_S.gguf new file mode 100644 index 0000000..fd60596 --- /dev/null +++ b/Gemma-2B-Alpaca.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f2ae85b59e50a7b6dcdb44891aa64fdc3ce73af55d9c1773f31b4c5dd4bf73 +size 1798915968 diff --git a/Gemma-2B-Alpaca.Q6_K.gguf b/Gemma-2B-Alpaca.Q6_K.gguf new file mode 100644 index 0000000..1dc1b00 --- /dev/null +++ b/Gemma-2B-Alpaca.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d0573942d0106285d3b0b25bca2121559213a848fa01b77d0beb4923c09f98f +size 2062124928 diff --git a/Gemma-2B-Alpaca.Q8_0.gguf b/Gemma-2B-Alpaca.Q8_0.gguf new file mode 100644 index 0000000..edf2ecf --- /dev/null +++ b/Gemma-2B-Alpaca.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0397e0d1f2629f3bcebb2447094f593e1d9bc61b263b3ac2b12765842c0da216 +size 2669070208 diff --git a/Gemma-2B-Alpaca.f16.gguf b/Gemma-2B-Alpaca.f16.gguf new file mode 100644 index 0000000..06515da --- /dev/null +++ b/Gemma-2B-Alpaca.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7425e0d782512af8fd0777d2865616b4186de768fa8f82438c1e0c754a0d22d +size 5018535808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8376c46 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Ttimofeyka/Gemma-2B-Alpaca +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Ttimofeyka/Gemma-2B-Alpaca + + +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/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2B-Alpaca-GGUF/resolve/main/Gemma-2B-Alpaca.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. + +