commit fa0af9091136f1a2bed3b43405f4f63bd251c6f8 Author: ModelHub XC Date: Sun Jun 14 22:58:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Katana-8b-sce-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..09356a0 --- /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 +Katana-8b-sce.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.f16.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Katana-8b-sce.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Katana-8b-sce.IQ4_XS.gguf b/Katana-8b-sce.IQ4_XS.gguf new file mode 100644 index 0000000..41994de --- /dev/null +++ b/Katana-8b-sce.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64feff4c5dd57d6e1ce84ad22f0cfa749ea1abb19eb91153d94e88cdda616d7b +size 4484363872 diff --git a/Katana-8b-sce.Q2_K.gguf b/Katana-8b-sce.Q2_K.gguf new file mode 100644 index 0000000..f671f5e --- /dev/null +++ b/Katana-8b-sce.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f2ee3fba4d197e69fcbf320974d7399f2a86efbdb3068a686ec7f39b4bada28 +size 3179132512 diff --git a/Katana-8b-sce.Q3_K_L.gguf b/Katana-8b-sce.Q3_K_L.gguf new file mode 100644 index 0000000..1839b16 --- /dev/null +++ b/Katana-8b-sce.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4d9db518119eacdb45c655d5f23203d75df7e5af0dc9aa7ee33a030edddcc3 +size 4321957472 diff --git a/Katana-8b-sce.Q3_K_M.gguf b/Katana-8b-sce.Q3_K_M.gguf new file mode 100644 index 0000000..41cc3c0 --- /dev/null +++ b/Katana-8b-sce.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9ec035bfd6a9b7a286431027ed45998775169fe3d8e45d913c26c8b229d3ec4 +size 4018919008 diff --git a/Katana-8b-sce.Q3_K_S.gguf b/Katana-8b-sce.Q3_K_S.gguf new file mode 100644 index 0000000..2b5769e --- /dev/null +++ b/Katana-8b-sce.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ec8d855638d88c26c748cd7214e49579aaa97b699f53b2dbd8655284571075 +size 3664500320 diff --git a/Katana-8b-sce.Q4_K_M.gguf b/Katana-8b-sce.Q4_K_M.gguf new file mode 100644 index 0000000..902eaae --- /dev/null +++ b/Katana-8b-sce.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22075a352bc1e762e928762aa9922e74da2187010464705be7702bda731c5a3b +size 4920735328 diff --git a/Katana-8b-sce.Q4_K_S.gguf b/Katana-8b-sce.Q4_K_S.gguf new file mode 100644 index 0000000..65d12f4 --- /dev/null +++ b/Katana-8b-sce.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a615276364db1a4403b0527e4e546e8b3e37be2a7dd69094694f99ff3d686467 +size 4692670048 diff --git a/Katana-8b-sce.Q5_K_M.gguf b/Katana-8b-sce.Q5_K_M.gguf new file mode 100644 index 0000000..726eb02 --- /dev/null +++ b/Katana-8b-sce.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3023dec7994fe5246ae4956b2186a1927b1ab8847871531ee15e782e30db0e41 +size 5732988512 diff --git a/Katana-8b-sce.Q5_K_S.gguf b/Katana-8b-sce.Q5_K_S.gguf new file mode 100644 index 0000000..1b5d893 --- /dev/null +++ b/Katana-8b-sce.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8bf956a06d9c93e21e6113e3a20597bd53c04173fe6c918373bd35e6fe58c3 +size 5599295072 diff --git a/Katana-8b-sce.Q6_K.gguf b/Katana-8b-sce.Q6_K.gguf new file mode 100644 index 0000000..560bc38 --- /dev/null +++ b/Katana-8b-sce.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef42b02288332d897a134be079882aec8cba0a411cf0b2ef77259c9050cf16d +size 6596007520 diff --git a/Katana-8b-sce.Q8_0.gguf b/Katana-8b-sce.Q8_0.gguf new file mode 100644 index 0000000..95a2353 --- /dev/null +++ b/Katana-8b-sce.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1778c8e20cffca82274e148e34759c9f97c84d268f1740ff72d040806dc673bf +size 8540771936 diff --git a/Katana-8b-sce.f16.gguf b/Katana-8b-sce.f16.gguf new file mode 100644 index 0000000..181b46b --- /dev/null +++ b/Katana-8b-sce.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187302dff6e3babac3b5fe904a646b6e19b271c1cf746451d2f1aaa38b18d785 +size 16068892256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d755188 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Quazim0t0/Katana-8b-sce +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +--- +## About + + + + + + +static quants of https://huggingface.co/Quazim0t0/Katana-8b-sce + + +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/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Katana-8b-sce-GGUF/resolve/main/Katana-8b-sce.f16.gguf) | f16 | 16.2 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +