commit 293264a351ff296432c5ef02f470eaa7c82264da Author: ModelHub XC Date: Fri Apr 24 14:45:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma2F16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..32060b9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Gemma2F16.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2F16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma2F16.IQ3_M.gguf b/Gemma2F16.IQ3_M.gguf new file mode 100644 index 0000000..01de06a --- /dev/null +++ b/Gemma2F16.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0674785ad545b59e7d0eae46eb5edbb3b54b6de27af88f8bead5ef859d67f6b7 +size 1393562112 diff --git a/Gemma2F16.IQ3_S.gguf b/Gemma2F16.IQ3_S.gguf new file mode 100644 index 0000000..b7b9c4c --- /dev/null +++ b/Gemma2F16.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84526fde5d5680f9dc91b1461433734d4b2eb124ccc2640923eb5dee46789d24 +size 1360660992 diff --git a/Gemma2F16.IQ3_XS.gguf b/Gemma2F16.IQ3_XS.gguf new file mode 100644 index 0000000..d7f727b --- /dev/null +++ b/Gemma2F16.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f236d755ecfc0bb7e1c5404ce3443c348c85a71b9d65a320c83fc6c5407d094 +size 1314212352 diff --git a/Gemma2F16.IQ4_XS.gguf b/Gemma2F16.IQ4_XS.gguf new file mode 100644 index 0000000..c47efc0 --- /dev/null +++ b/Gemma2F16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c509492de54e97273f4ffb70f824f224d10c988f747648800afc46ed0ddb4eb +size 1576204800 diff --git a/Gemma2F16.Q2_K.gguf b/Gemma2F16.Q2_K.gguf new file mode 100644 index 0000000..0b39d27 --- /dev/null +++ b/Gemma2F16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f598075fa180122e2f062c54e6c10c068af1bb8c895995447c239ce85e94471d +size 1229830656 diff --git a/Gemma2F16.Q3_K_L.gguf b/Gemma2F16.Q3_K_L.gguf new file mode 100644 index 0000000..2c6f98c --- /dev/null +++ b/Gemma2F16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367661a42d9a9a60b5aa1a424b8af82dd048223a4b9ada011efc4305b72a9373 +size 1550436864 diff --git a/Gemma2F16.Q3_K_M.gguf b/Gemma2F16.Q3_K_M.gguf new file mode 100644 index 0000000..9d29e77 --- /dev/null +++ b/Gemma2F16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a0594ed2daf2badc36a45dae06fb87103fcdefa2ef3428d6911be67f7567e1 +size 1461668352 diff --git a/Gemma2F16.Q3_K_S.gguf b/Gemma2F16.Q3_K_S.gguf new file mode 100644 index 0000000..6174453 --- /dev/null +++ b/Gemma2F16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d9241832583069aab9c8cee77ac89cf670d672fd0cf86469fa081c620d6ea13 +size 1360660992 diff --git a/Gemma2F16.Q4_K_M.gguf b/Gemma2F16.Q4_K_M.gguf new file mode 100644 index 0000000..44aef50 --- /dev/null +++ b/Gemma2F16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a53200e473f882cd4e575df065e189763563ba31bf865148f2006733b928f11 +size 1708583424 diff --git a/Gemma2F16.Q4_K_S.gguf b/Gemma2F16.Q4_K_S.gguf new file mode 100644 index 0000000..b5a400f --- /dev/null +++ b/Gemma2F16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af091d4196b0c73218cc42c39a4d1316c9ffe6fdda2f28f1055abb6544c8c0d0 +size 1638652416 diff --git a/Gemma2F16.Q5_K_M.gguf b/Gemma2F16.Q5_K_M.gguf new file mode 100644 index 0000000..0f6b2a2 --- /dev/null +++ b/Gemma2F16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed9736f8774977f004f6106177179e57a4398829cd8304e8a6a9c1fc86ba0ee3 +size 1923279360 diff --git a/Gemma2F16.Q5_K_S.gguf b/Gemma2F16.Q5_K_S.gguf new file mode 100644 index 0000000..f6f7e10 --- /dev/null +++ b/Gemma2F16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61e5eaf28d8ad93e3ee41d57280c8218d5ac55c6da33648de8c65426624cb4ca +size 1882544640 diff --git a/Gemma2F16.Q6_K.gguf b/Gemma2F16.Q6_K.gguf new file mode 100644 index 0000000..f8788bb --- /dev/null +++ b/Gemma2F16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11aa0c940a91ef4f2db2e599e0cf17ea18dde3e2e2c9ff3231249ad837e7904c +size 2151393792 diff --git a/Gemma2F16.Q8_0.gguf b/Gemma2F16.Q8_0.gguf new file mode 100644 index 0000000..7118972 --- /dev/null +++ b/Gemma2F16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:144194c7d27d9be9be79e316846cca98c380b6e6ae4198a89c906a9fc3f1e5e6 +size 2784496128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..01764d5 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: ReplaceHumanWithAI/Gemma2F16 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/ReplaceHumanWithAI/Gemma2F16 + + +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/Gemma2F16-GGUF/resolve/main/Gemma2F16.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.IQ3_XS.gguf) | IQ3_XS | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.IQ3_S.gguf) | IQ3_S | 1.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.Q3_K_S.gguf) | Q3_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.IQ3_M.gguf) | IQ3_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.IQ4_XS.gguf) | IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.Q5_K_M.gguf) | Q5_K_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma2F16-GGUF/resolve/main/Gemma2F16.Q8_0.gguf) | Q8_0 | 2.9 | fast, best quality | + +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. + +