commit b59e4cfb52928a0e49961a2779c13e2f6e796558 Author: ModelHub XC Date: Sat Jun 20 16:26:20 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/KAT-V1-40B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..226b8d4 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +KAT-V1-40B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KAT-V1-40B.i1-IQ1_M.gguf b/KAT-V1-40B.i1-IQ1_M.gguf new file mode 100644 index 0000000..28edf99 --- /dev/null +++ b/KAT-V1-40B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20b67e593bad58080dbb9c0f420828f27d25768d7b47dd0217d30d1253d55a0 +size 9716030816 diff --git a/KAT-V1-40B.i1-IQ1_S.gguf b/KAT-V1-40B.i1-IQ1_S.gguf new file mode 100644 index 0000000..5588149 --- /dev/null +++ b/KAT-V1-40B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e339f37e03e80a0e186c8f892caeade1c258262457e22c9d7878e39dc788a998 +size 8893963616 diff --git a/KAT-V1-40B.i1-IQ2_M.gguf b/KAT-V1-40B.i1-IQ2_M.gguf new file mode 100644 index 0000000..4f9a340 --- /dev/null +++ b/KAT-V1-40B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fef7c2eca8942140a142d65406b7139c27f1305166f218e1bc8c2fe2806677f +size 13861612896 diff --git a/KAT-V1-40B.i1-IQ2_S.gguf b/KAT-V1-40B.i1-IQ2_S.gguf new file mode 100644 index 0000000..d59dafa --- /dev/null +++ b/KAT-V1-40B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:917d1c933dad29de58578e7e4e36a4bae2f6585f84659eb779f6160744903522 +size 12765523296 diff --git a/KAT-V1-40B.i1-IQ2_XS.gguf b/KAT-V1-40B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d548a43 --- /dev/null +++ b/KAT-V1-40B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1647015f5650780bb259186b8151cc005332e1a97d08073d00de899e75957cc8 +size 12247768416 diff --git a/KAT-V1-40B.i1-IQ2_XXS.gguf b/KAT-V1-40B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..62b52b3 --- /dev/null +++ b/KAT-V1-40B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc263b6764a117d2b14798c0bd351c8cb53c01d36439e0febc4c9f451f168cf +size 11086142816 diff --git a/KAT-V1-40B.i1-IQ3_M.gguf b/KAT-V1-40B.i1-IQ3_M.gguf new file mode 100644 index 0000000..c3c0f39 --- /dev/null +++ b/KAT-V1-40B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88424659e41b2acdc7c24ffca71603b5893816b5655637f576fc7d198733c503 +size 18320293216 diff --git a/KAT-V1-40B.i1-IQ3_S.gguf b/KAT-V1-40B.i1-IQ3_S.gguf new file mode 100644 index 0000000..6012df2 --- /dev/null +++ b/KAT-V1-40B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:653d869f4027c029d8ded623db8c8fe923afb9ea685d6d8cbd6c729500601460 +size 17853758816 diff --git a/KAT-V1-40B.i1-IQ3_XS.gguf b/KAT-V1-40B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0ae245b --- /dev/null +++ b/KAT-V1-40B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e193c1d2781ee438185a79dad702ca4c26cb43d7992e6f5a4dc6f61118c06754 +size 16939531616 diff --git a/KAT-V1-40B.i1-IQ3_XXS.gguf b/KAT-V1-40B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3cb7c5d --- /dev/null +++ b/KAT-V1-40B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e78c79f43b7c1321fec67b369cb2c3f09c8388990669f280ff669d9f471de0 +size 15882579296 diff --git a/KAT-V1-40B.i1-IQ4_XS.gguf b/KAT-V1-40B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..f6f75d2 --- /dev/null +++ b/KAT-V1-40B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0108f9fdb4673df7092fff15eedc2794f20d4ab040d8e52ff95f648c7cafdbf +size 21851884896 diff --git a/KAT-V1-40B.i1-Q2_K.gguf b/KAT-V1-40B.i1-Q2_K.gguf new file mode 100644 index 0000000..2ae30c9 --- /dev/null +++ b/KAT-V1-40B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea3bdfa6a3c24d12861ae3fd3685b25025742eeab846e6a87ebf3318f344817 +size 15218781536 diff --git a/KAT-V1-40B.i1-Q2_K_S.gguf b/KAT-V1-40B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..aef2058 --- /dev/null +++ b/KAT-V1-40B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cf9d012c92aa6303228395c02bc5c39976efb4cf74ccd44bbaf1cd5e5dff8f1 +size 14187408736 diff --git a/KAT-V1-40B.i1-Q3_K_L.gguf b/KAT-V1-40B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1299ccf --- /dev/null +++ b/KAT-V1-40B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f83ee7b5af3fe5366c4f34b80a30c55b44c6acbba17b2a077d9fd40219254b2 +size 21314059616 diff --git a/KAT-V1-40B.i1-Q3_K_M.gguf b/KAT-V1-40B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a79d578 --- /dev/null +++ b/KAT-V1-40B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562432f9e03ecd68207fe951006e7fdc4c2bdb85013c7ceda7a7256e99592fb9 +size 19724811616 diff --git a/KAT-V1-40B.i1-Q3_K_S.gguf b/KAT-V1-40B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..65d8575 --- /dev/null +++ b/KAT-V1-40B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a038c771189d3e8541df83ba509395419896251a297093d56b731fae325d7f7 +size 17853758816 diff --git a/KAT-V1-40B.i1-Q4_0.gguf b/KAT-V1-40B.i1-Q4_0.gguf new file mode 100644 index 0000000..73e415e --- /dev/null +++ b/KAT-V1-40B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1342af27c018a57eb7307782007905f380a4b9fb19fd3e841a656f0ae9b8477e +size 23118122336 diff --git a/KAT-V1-40B.i1-Q4_1.gguf b/KAT-V1-40B.i1-Q4_1.gguf new file mode 100644 index 0000000..881989a --- /dev/null +++ b/KAT-V1-40B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4fb81a6b48d785ce1461ea2b1504985f933853a45d7f0ebff00d2b464d6062c +size 25516248416 diff --git a/KAT-V1-40B.i1-Q4_K_M.gguf b/KAT-V1-40B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..2872e36 --- /dev/null +++ b/KAT-V1-40B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8d9cbd72b88b87080d5b8f9a8e2e551bdbf14cf0cc9f2d84d65c3cceb5b746 +size 24569744736 diff --git a/KAT-V1-40B.i1-Q4_K_S.gguf b/KAT-V1-40B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..46c61f6 --- /dev/null +++ b/KAT-V1-40B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9eea12ea3db513bed1210b91437c97e8539a14e5cee59c8fa3690f9eb3eeb52 +size 23259024736 diff --git a/KAT-V1-40B.i1-Q5_K_M.gguf b/KAT-V1-40B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8ee2c92 --- /dev/null +++ b/KAT-V1-40B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7690fb2502008528cdb4cda48f8c555941fad344ae3e6f9388be7c0ccf259e3a +size 28782726496 diff --git a/KAT-V1-40B.i1-Q5_K_S.gguf b/KAT-V1-40B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..983db2b --- /dev/null +++ b/KAT-V1-40B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:180b8b3735802a86c1155bcecace41f20edb437e918673b23e5f07b1d7342623 +size 28002848096 diff --git a/KAT-V1-40B.i1-Q6_K.gguf b/KAT-V1-40B.i1-Q6_K.gguf new file mode 100644 index 0000000..874f2e8 --- /dev/null +++ b/KAT-V1-40B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a67757d4b2e3dd7897fb7b276218ee4e6f08372bcb37f53ead33b4949851b9f2 +size 33286872416 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3ceabaf --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: Kwaipilot/KAT-V1-40B +language: +- multilingual +library_name: transformers +license: other +license_link: LICENSE +license_name: kwaipilot-license +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Kwaipilot/KAT-V1-40B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KAT-V1-40B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/KAT-V1-40B-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/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ1_S.gguf) | i1-IQ1_S | 9.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ1_M.gguf) | i1-IQ1_M | 9.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 11.2 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.3 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ2_S.gguf) | i1-IQ2_S | 12.9 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ2_M.gguf) | i1-IQ2_M | 14.0 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 14.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q2_K.gguf) | i1-Q2_K | 15.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 16.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 17.0 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ3_S.gguf) | i1-IQ3_S | 18.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 18.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ3_M.gguf) | i1-IQ3_M | 18.4 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 19.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 21.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 22.0 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q4_0.gguf) | i1-Q4_0 | 23.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 23.4 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 24.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q4_1.gguf) | i1-Q4_1 | 25.6 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 28.1 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 28.9 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-V1-40B-i1-GGUF/resolve/main/KAT-V1-40B.i1-Q6_K.gguf) | i1-Q6_K | 33.4 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..a45b8f3 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5a7a579c24c7969abb5f6e39a09e0490b22d6e50c05f7aeafbeff5d64108000 +size 18696365