commit 8be533db67c32fe6aad7f2b83785c4ac13124144 Author: ModelHub XC Date: Tue Jun 30 22:06:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma2-9B-KuwaNovelist-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ab1a207 --- /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 +Gemma2-9B-KuwaNovelist.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.f16.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma2-9B-KuwaNovelist.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma2-9B-KuwaNovelist.IQ4_XS.gguf b/Gemma2-9B-KuwaNovelist.IQ4_XS.gguf new file mode 100644 index 0000000..d4b9749 --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d088feac00424d81199b46f1dab1184f26389af129360366b5712e10b2dacbc0 +size 5223171936 diff --git a/Gemma2-9B-KuwaNovelist.Q2_K.gguf b/Gemma2-9B-KuwaNovelist.Q2_K.gguf new file mode 100644 index 0000000..e7ddd51 --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50a8d8b8341479ae64e4cdce38897fc63b4fc00004ccaa3a4c4a47a44964eca8 +size 3805398880 diff --git a/Gemma2-9B-KuwaNovelist.Q3_K_L.gguf b/Gemma2-9B-KuwaNovelist.Q3_K_L.gguf new file mode 100644 index 0000000..95c4858 --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87eb0d625874c9efc7dde005040e93c9b2d1c426becf7264dd1abab5d46973a3 +size 5132453728 diff --git a/Gemma2-9B-KuwaNovelist.Q3_K_M.gguf b/Gemma2-9B-KuwaNovelist.Q3_K_M.gguf new file mode 100644 index 0000000..90f734f --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26531d55cca81b667025f9256c91e3019d3dd06833869e404b3370370ca5dbeb +size 4761782112 diff --git a/Gemma2-9B-KuwaNovelist.Q3_K_S.gguf b/Gemma2-9B-KuwaNovelist.Q3_K_S.gguf new file mode 100644 index 0000000..6402030 --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c06a3c37985182749821b609d2160485d2f7d2b2cc85c627ed108d67ee4997ed +size 4337665888 diff --git a/Gemma2-9B-KuwaNovelist.Q4_K_M.gguf b/Gemma2-9B-KuwaNovelist.Q4_K_M.gguf new file mode 100644 index 0000000..7f219f2 --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c050a769c5d2c8f6417c83238955e171d4b12e16ca2c389fa851ebcf2f8a603 +size 5761058656 diff --git a/Gemma2-9B-KuwaNovelist.Q4_K_S.gguf b/Gemma2-9B-KuwaNovelist.Q4_K_S.gguf new file mode 100644 index 0000000..4587ba9 --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d48c12172c0bad35ff662a89fb27b1a13cb4362b97502a4277ac3ca02bd99d +size 5478926176 diff --git a/Gemma2-9B-KuwaNovelist.Q5_K_M.gguf b/Gemma2-9B-KuwaNovelist.Q5_K_M.gguf new file mode 100644 index 0000000..8c50f98 --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8750dcb79ace574da49e6577e42e1e4408da6e8890300ae955a38aac19458c6 +size 6647367520 diff --git a/Gemma2-9B-KuwaNovelist.Q5_K_S.gguf b/Gemma2-9B-KuwaNovelist.Q5_K_S.gguf new file mode 100644 index 0000000..714e54f --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35c7fdd5892619f8b62cd722d91f77cab4ad931c7cd5bbc2dce33050df294507 +size 6483593056 diff --git a/Gemma2-9B-KuwaNovelist.Q6_K.gguf b/Gemma2-9B-KuwaNovelist.Q6_K.gguf new file mode 100644 index 0000000..fb98b10 --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a027dfc99175541d729618d237844c355f506e96a103024ea8146aea2627ab +size 7589070688 diff --git a/Gemma2-9B-KuwaNovelist.Q8_0.gguf b/Gemma2-9B-KuwaNovelist.Q8_0.gguf new file mode 100644 index 0000000..23f2b75 --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f7e26c6b7d7f918f4c43b408de5db8bc7150b79f162bbc78aa64f3c539e94dd +size 9827149664 diff --git a/Gemma2-9B-KuwaNovelist.f16.gguf b/Gemma2-9B-KuwaNovelist.f16.gguf new file mode 100644 index 0000000..e6868ae --- /dev/null +++ b/Gemma2-9B-KuwaNovelist.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ac7a40309f17fcb05ee4efbb9764d8a5efa0a50000b9edc25264c3bfd52fe41 +size 18490681184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7559237 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Alsebay/Gemma2-9B-KuwaNovelist +language: +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Alsebay/Gemma2-9B-KuwaNovelist + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-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/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma2-9B-KuwaNovelist-GGUF/resolve/main/Gemma2-9B-KuwaNovelist.f16.gguf) | f16 | 18.6 | 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. + +