commit ec1a3cf7de31dd2a0cc3b9cbafa488357be7f288 Author: ModelHub XC Date: Mon Jun 15 08:14:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-7b-aps-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..56ab17a --- /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-7b-aps-it.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-aps-it.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b629034 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: google/gemma-7b-aps-it +extra_gated_button_content: Acknowledge license +extra_gated_heading: Access Gemma on Hugging Face +extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and + agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging + Face and click below. Requests are processed immediately. +language: +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/google/gemma-7b-aps-it + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-7b-aps-it-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-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.Q2_K.gguf) | Q2_K | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.Q3_K_S.gguf) | Q3_K_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.Q5_K_S.gguf) | Q5_K_S | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-aps-it-GGUF/resolve/main/gemma-7b-aps-it.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/gemma-7b-aps-it.IQ4_XS.gguf b/gemma-7b-aps-it.IQ4_XS.gguf new file mode 100644 index 0000000..26204da --- /dev/null +++ b/gemma-7b-aps-it.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66078150567116273d0309a8bfea2ff72b28f98abcfcbca74bbcd548eaede551 +size 4805012864 diff --git a/gemma-7b-aps-it.Q2_K.gguf b/gemma-7b-aps-it.Q2_K.gguf new file mode 100644 index 0000000..8577aff --- /dev/null +++ b/gemma-7b-aps-it.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5153949dca0168aa43205ee9bfce45315e38da06e9d9ffcaec0f3086787ca466 +size 3481447808 diff --git a/gemma-7b-aps-it.Q3_K_L.gguf b/gemma-7b-aps-it.Q3_K_L.gguf new file mode 100644 index 0000000..811ef7d --- /dev/null +++ b/gemma-7b-aps-it.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715e8045d505abdfc39eb4480d317f53e888a685ffcce0b1ba6430fa21074b77 +size 4709068160 diff --git a/gemma-7b-aps-it.Q3_K_M.gguf b/gemma-7b-aps-it.Q3_K_M.gguf new file mode 100644 index 0000000..2dadc58 --- /dev/null +++ b/gemma-7b-aps-it.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725c81c65195f9c569086df95e40fb9fae66572862c9b1e203e3c952769c029b +size 4369329536 diff --git a/gemma-7b-aps-it.Q3_K_S.gguf b/gemma-7b-aps-it.Q3_K_S.gguf new file mode 100644 index 0000000..9d61f2b --- /dev/null +++ b/gemma-7b-aps-it.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aebacf4773c2f5582f8b8d19dcc708646291aa56bc4fa37df5c6abf59464e85 +size 3982404992 diff --git a/gemma-7b-aps-it.Q4_K_M.gguf b/gemma-7b-aps-it.Q4_K_M.gguf new file mode 100644 index 0000000..418bf10 --- /dev/null +++ b/gemma-7b-aps-it.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df85154d427d9c4382bdd61f4229dcc5f416e6def580241615b91520583fa26 +size 5329759616 diff --git a/gemma-7b-aps-it.Q4_K_S.gguf b/gemma-7b-aps-it.Q4_K_S.gguf new file mode 100644 index 0000000..de3c7ad --- /dev/null +++ b/gemma-7b-aps-it.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a368bb37f358fef5699e46d45b52b718177222aea213eb1e7024d3723d212624 +size 5046447488 diff --git a/gemma-7b-aps-it.Q5_K_M.gguf b/gemma-7b-aps-it.Q5_K_M.gguf new file mode 100644 index 0000000..6e6520c --- /dev/null +++ b/gemma-7b-aps-it.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95948aab74635f566efd6f3f0dac818817f0d63f5c4a7ce643bbb05f8b73c3e8 +size 6144503168 diff --git a/gemma-7b-aps-it.Q5_K_S.gguf b/gemma-7b-aps-it.Q5_K_S.gguf new file mode 100644 index 0000000..4c18830 --- /dev/null +++ b/gemma-7b-aps-it.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d22b53feec8e8109bc28ce7a91310d786ea30311b0502bcde4c3d4dab735c801 +size 5980728704 diff --git a/gemma-7b-aps-it.Q6_K.gguf b/gemma-7b-aps-it.Q6_K.gguf new file mode 100644 index 0000000..971db79 --- /dev/null +++ b/gemma-7b-aps-it.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afef20c292ea594f4de3d1a13ac8e5a0283c116e218e8d0ea7c047b1c903d8d2 +size 7010168192 diff --git a/gemma-7b-aps-it.Q8_0.gguf b/gemma-7b-aps-it.Q8_0.gguf new file mode 100644 index 0000000..099e961 --- /dev/null +++ b/gemma-7b-aps-it.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c13284936369b8ab0f40e8829c89a2e0041967fb836f7b2cb797ca92b3b3d822 +size 9077845376 diff --git a/gemma-7b-aps-it.f16.gguf b/gemma-7b-aps-it.f16.gguf new file mode 100644 index 0000000..83d35fd --- /dev/null +++ b/gemma-7b-aps-it.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a76fa30a898e86d971016c2fb88b478661dd494d18b6055b05e11c94e54e4822 +size 17081757056