commit 39cfbc6756fb996f2fe9d411fd3f2c7c85c96f2d Author: ModelHub XC Date: Wed May 13 01:26:37 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Koto-22B-PT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d475333 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Koto-22B-PT.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Koto-22B-PT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Koto-22B-PT.i1-IQ1_M.gguf b/Koto-22B-PT.i1-IQ1_M.gguf new file mode 100644 index 0000000..ae03f84 --- /dev/null +++ b/Koto-22B-PT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9b487cdde36fee977ce54a6bde77c86f38f00dc5362ad20b172bab9382a6bde +size 5496572608 diff --git a/Koto-22B-PT.i1-IQ1_S.gguf b/Koto-22B-PT.i1-IQ1_S.gguf new file mode 100644 index 0000000..69af72a --- /dev/null +++ b/Koto-22B-PT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d9e2b62dceb5355777edd3b9e2d33898f13610eddb790994ae461c3728ea12f +size 5073128128 diff --git a/Koto-22B-PT.i1-IQ2_M.gguf b/Koto-22B-PT.i1-IQ2_M.gguf new file mode 100644 index 0000000..52e1cbb --- /dev/null +++ b/Koto-22B-PT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f98da3fbef7bc3179dbaabd9edf6bd2da3841893b28e4b901114cffd1f231ab +size 7740690144 diff --git a/Koto-22B-PT.i1-IQ2_S.gguf b/Koto-22B-PT.i1-IQ2_S.gguf new file mode 100644 index 0000000..9c21d01 --- /dev/null +++ b/Koto-22B-PT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:096bcabddfb1206981770397a4b5c441117433b19ea5cbd5e0aaeaf9bbb9b5ef +size 7176097504 diff --git a/Koto-22B-PT.i1-IQ2_XS.gguf b/Koto-22B-PT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6f6bb90 --- /dev/null +++ b/Koto-22B-PT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17e1322c0a8f61247c462cdc0b690d34f426e071caa0bd944c38df369f11be3c +size 6816713408 diff --git a/Koto-22B-PT.i1-IQ2_XXS.gguf b/Koto-22B-PT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..44684b9 --- /dev/null +++ b/Koto-22B-PT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee70c17d1852603a1e2491ac282d551721f12f04dbc7742024216f900ce05fd +size 6202313408 diff --git a/Koto-22B-PT.i1-IQ3_M.gguf b/Koto-22B-PT.i1-IQ3_M.gguf new file mode 100644 index 0000000..e667bed --- /dev/null +++ b/Koto-22B-PT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc8e570ae46be3a5ae19072622ebfd9e4e0119ed69b07aebd06fc3462d8ddf5b +size 10105312320 diff --git a/Koto-22B-PT.i1-IQ3_S.gguf b/Koto-22B-PT.i1-IQ3_S.gguf new file mode 100644 index 0000000..c50e8b1 --- /dev/null +++ b/Koto-22B-PT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42596a0ea8f5a6f2a28957f750c54df4ee02427050d95a70794eb87e1fd0a5ff +size 9805894720 diff --git a/Koto-22B-PT.i1-IQ3_XS.gguf b/Koto-22B-PT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ba1f696 --- /dev/null +++ b/Koto-22B-PT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c96da8051e93d443871d52a375605717569f601ae4f337893be0df94ffe204b7 +size 9320272960 diff --git a/Koto-22B-PT.i1-IQ3_XXS.gguf b/Koto-22B-PT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..eb5fd21 --- /dev/null +++ b/Koto-22B-PT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050e0a70d87ac70969642a6e8e1eccf8ec485062e36256cefcc894b34d5180c9 +size 8714391264 diff --git a/Koto-22B-PT.i1-IQ4_XS.gguf b/Koto-22B-PT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..94d9d98 --- /dev/null +++ b/Koto-22B-PT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0915e75d78fea587cd9bf800cb4e931e79caf8ce9837f69ba9f4893e486dd7c +size 11987753024 diff --git a/Koto-22B-PT.i1-Q2_K.gguf b/Koto-22B-PT.i1-Q2_K.gguf new file mode 100644 index 0000000..3b84ecf --- /dev/null +++ b/Koto-22B-PT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e693282af1fbc60974f4ac402015d668ec0678beca2c8616fd8dc6df39e91800 +size 8402276384 diff --git a/Koto-22B-PT.i1-Q2_K_S.gguf b/Koto-22B-PT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..1b7f70d --- /dev/null +++ b/Koto-22B-PT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62781fa372cf16fe16f73d39e4561bbc7a8e89feb2f2959bb9d83690bc7651ba +size 7828672544 diff --git a/Koto-22B-PT.i1-Q3_K_L.gguf b/Koto-22B-PT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4914b93 --- /dev/null +++ b/Koto-22B-PT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:042bb3f6cca6d11f4905b956458a8e00030ca940e87701f270e4e4fd1405f35a +size 11704800320 diff --git a/Koto-22B-PT.i1-Q3_K_M.gguf b/Koto-22B-PT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..613b14c --- /dev/null +++ b/Koto-22B-PT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b7897c7816b360bfeb26a734fe50458fdde0d0272c6acb49d008c309630cb27 +size 10796471360 diff --git a/Koto-22B-PT.i1-Q3_K_S.gguf b/Koto-22B-PT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..cf77d15 --- /dev/null +++ b/Koto-22B-PT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb499168fb48bacd8b5d7578b4e73e7b430056dd7305c4f6a6bef79de8ed5cfd +size 9752974400 diff --git a/Koto-22B-PT.i1-Q4_0.gguf b/Koto-22B-PT.i1-Q4_0.gguf new file mode 100644 index 0000000..8c3985d --- /dev/null +++ b/Koto-22B-PT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1dd3e511404e4abd45679d7f07a5377f0e9c90055f7419668cb65af435c4c13 +size 12635249024 diff --git a/Koto-22B-PT.i1-Q4_1.gguf b/Koto-22B-PT.i1-Q4_1.gguf new file mode 100644 index 0000000..e8408e5 --- /dev/null +++ b/Koto-22B-PT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea2ec18a0d24d6b96060fdfccec6da59db5bdbf7051fe8eb7638c42419892715 +size 13930896384 diff --git a/Koto-22B-PT.i1-Q4_K_M.gguf b/Koto-22B-PT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..607542d --- /dev/null +++ b/Koto-22B-PT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:209971fe83983753eae3d9fdb8054e7052b167731cfd8dccd3c927086209c0cb +size 13364418944 diff --git a/Koto-22B-PT.i1-Q4_K_S.gguf b/Koto-22B-PT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d68af98 --- /dev/null +++ b/Koto-22B-PT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68a85a82e8d05c4a89381c666d81b2c849ff8e81eb971dadba2fd7ac58e78413 +size 12679158144 diff --git a/Koto-22B-PT.i1-Q5_K_M.gguf b/Koto-22B-PT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..333ff58 --- /dev/null +++ b/Koto-22B-PT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bddbd7f8b5a4b94b689bfee81f9119e3811830fd6ab50ad8caaf59866064f2d +size 15664733824 diff --git a/Koto-22B-PT.i1-Q5_K_S.gguf b/Koto-22B-PT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3d221dc --- /dev/null +++ b/Koto-22B-PT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8870ee3d7417c042063d3185dc458e7f7b24d2895c5f7d33c78758d8172fec4 +size 15267831424 diff --git a/Koto-22B-PT.i1-Q6_K.gguf b/Koto-22B-PT.i1-Q6_K.gguf new file mode 100644 index 0000000..4508ead --- /dev/null +++ b/Koto-22B-PT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa83435afbff8ab20ce9794f66742caccf57b1d9eb4596ec4cc18b51c08bd0c7 +size 18108818400 diff --git a/Koto-22B-PT.imatrix.gguf b/Koto-22B-PT.imatrix.gguf new file mode 100644 index 0000000..328fa38 --- /dev/null +++ b/Koto-22B-PT.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f0ec345c4e065e754c8d1551c961347b9b5ad1b4769069729916a30eba8c2d9 +size 13467520 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6fd882e --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: allura-org/Koto-22B-PT +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- writing +- creative-writing +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/allura-org/Koto-22B-PT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Koto-22B-PT-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Koto-22B-PT-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/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ1_S.gguf) | i1-IQ1_S | 5.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ1_M.gguf) | i1-IQ1_M | 5.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ2_S.gguf) | i1-IQ2_S | 7.3 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ2_M.gguf) | i1-IQ2_M | 7.8 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 7.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q2_K.gguf) | i1-Q2_K | 8.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ3_S.gguf) | i1-IQ3_S | 9.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ3_M.gguf) | i1-IQ3_M | 10.2 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 11.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q4_0.gguf) | i1-Q4_0 | 12.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 12.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 13.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q4_1.gguf) | i1-Q4_1 | 14.0 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 15.4 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 15.8 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-22B-PT-i1-GGUF/resolve/main/Koto-22B-PT.i1-Q6_K.gguf) | i1-Q6_K | 18.2 | practically like static Q6_K | + +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. + +