commit 851b286c79308f9e4abbf1d86d0ab58a9af623b9 Author: ModelHub XC Date: Wed May 20 14:45:36 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/KAT-Dev-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eb9dd0a --- /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 +KAT-Dev.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +KAT-Dev.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KAT-Dev.i1-IQ1_M.gguf b/KAT-Dev.i1-IQ1_M.gguf new file mode 100644 index 0000000..d70a169 --- /dev/null +++ b/KAT-Dev.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b2385590e499e5e91f312b399c811faa448ee50608e793ad8413d6b5f5775b5 +size 7959870848 diff --git a/KAT-Dev.i1-IQ1_S.gguf b/KAT-Dev.i1-IQ1_S.gguf new file mode 100644 index 0000000..1810f4d --- /dev/null +++ b/KAT-Dev.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cce892bd397301682a3cb66a3fa370c2c840aeebf311861d3ef69aefca5ba61 +size 7323843968 diff --git a/KAT-Dev.i1-IQ2_M.gguf b/KAT-Dev.i1-IQ2_M.gguf new file mode 100644 index 0000000..1632071 --- /dev/null +++ b/KAT-Dev.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a049baac8d23725abb26c5aca42c3f350300252d564b2ccf7b819dd75d7ac4 +size 11362863488 diff --git a/KAT-Dev.i1-IQ2_S.gguf b/KAT-Dev.i1-IQ2_S.gguf new file mode 100644 index 0000000..4a2b6f1 --- /dev/null +++ b/KAT-Dev.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2897f6fe1a696c2cb0043ed09ec104a775a25cc0abe1eccb9e9bf7a0f4f6a72 +size 10514827648 diff --git a/KAT-Dev.i1-IQ2_XS.gguf b/KAT-Dev.i1-IQ2_XS.gguf new file mode 100644 index 0000000..771a695 --- /dev/null +++ b/KAT-Dev.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c0dfe94dce01cd85cce1559b7abbc5ee0e377d1d5d031170a07938d0786a6a5 +size 9951837568 diff --git a/KAT-Dev.i1-IQ2_XXS.gguf b/KAT-Dev.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..785ee68 --- /dev/null +++ b/KAT-Dev.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54c4f31e12336627146122c53da54f07ab9cf0b062f07a142289a2c490538c46 +size 9019915648 diff --git a/KAT-Dev.i1-IQ3_M.gguf b/KAT-Dev.i1-IQ3_M.gguf new file mode 100644 index 0000000..4b02745 --- /dev/null +++ b/KAT-Dev.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ccf7635957d074e952a664cf4c07b0cc7c53f3ebca79326e44e356b05a88f02 +size 14930085248 diff --git a/KAT-Dev.i1-IQ3_S.gguf b/KAT-Dev.i1-IQ3_S.gguf new file mode 100644 index 0000000..d692b27 --- /dev/null +++ b/KAT-Dev.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e615160037e46321a50aa6ed986e30ed73f28ac3f030c64a021e906fa5176ce4 +size 14434305408 diff --git a/KAT-Dev.i1-IQ3_XS.gguf b/KAT-Dev.i1-IQ3_XS.gguf new file mode 100644 index 0000000..3419394 --- /dev/null +++ b/KAT-Dev.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea52d5bec82de4b73325b728139476300944ba286ae849c1d1970c8d827f5d44 +size 13702923648 diff --git a/KAT-Dev.i1-IQ3_XXS.gguf b/KAT-Dev.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..7b7cbfc --- /dev/null +++ b/KAT-Dev.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39ce45c0e0dd5506d314b72837a4e1f711370aca076e29ea7df030bb4f5a9d8 +size 12821039488 diff --git a/KAT-Dev.i1-IQ4_XS.gguf b/KAT-Dev.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8aa6baf --- /dev/null +++ b/KAT-Dev.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a117d1da3a813c40560aa70d928a981a41c4001674774a08552862d70c33931 +size 17690497408 diff --git a/KAT-Dev.i1-Q2_K.gguf b/KAT-Dev.i1-Q2_K.gguf new file mode 100644 index 0000000..017cb37 --- /dev/null +++ b/KAT-Dev.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48faf04fc7d213a2ed88842f901921118a2a03eb7e8378191bead3a99195f084 +size 12344654208 diff --git a/KAT-Dev.i1-Q2_K_S.gguf b/KAT-Dev.i1-Q2_K_S.gguf new file mode 100644 index 0000000..21ec2ce --- /dev/null +++ b/KAT-Dev.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:031a1cb7eda97e6ed29ab62fe0e2bf238667377d7a10c8577e017a0b48a41ddc +size 11465816448 diff --git a/KAT-Dev.i1-Q3_K_L.gguf b/KAT-Dev.i1-Q3_K_L.gguf new file mode 100644 index 0000000..fa17100 --- /dev/null +++ b/KAT-Dev.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73dba90a82128a572e1f4b165fef04eeba0ec0fe5b0ed0f36a890509acdee907 +size 17330996608 diff --git a/KAT-Dev.i1-Q3_K_M.gguf b/KAT-Dev.i1-Q3_K_M.gguf new file mode 100644 index 0000000..6d75821 --- /dev/null +++ b/KAT-Dev.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c84758d13ebd4185e61a2e2ff02129f340b795a969dfae37fd16ff558784986 +size 15971779968 diff --git a/KAT-Dev.i1-Q3_K_S.gguf b/KAT-Dev.i1-Q3_K_S.gguf new file mode 100644 index 0000000..134e96f --- /dev/null +++ b/KAT-Dev.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5883c6be2539797cf0ac228e8271c56b347c2af7002e5c8b73f02bd933743006 +size 14389740928 diff --git a/KAT-Dev.i1-Q4_0.gguf b/KAT-Dev.i1-Q4_0.gguf new file mode 100644 index 0000000..e92d5dc --- /dev/null +++ b/KAT-Dev.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:811b010c7886d9af1a0a8f03a32505137ec43eb657d4f58d9a6a175f581be68e +size 18703090048 diff --git a/KAT-Dev.i1-Q4_1.gguf b/KAT-Dev.i1-Q4_1.gguf new file mode 100644 index 0000000..86eda57 --- /dev/null +++ b/KAT-Dev.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31095813432483ecfc306b6a7a863bbfc162490645582bfa40b4d6a6156bcbfb +size 20636524928 diff --git a/KAT-Dev.i1-Q4_K_M.gguf b/KAT-Dev.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f7f75ad --- /dev/null +++ b/KAT-Dev.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e768a4e898c656d44971dd97a640eb4c5453534d20e6a607b6c6c50b9f24461a +size 19762151808 diff --git a/KAT-Dev.i1-Q4_K_S.gguf b/KAT-Dev.i1-Q4_K_S.gguf new file mode 100644 index 0000000..89a074a --- /dev/null +++ b/KAT-Dev.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2ef0c5c6ad8176378c57a662d01b87fc849e23646f7b5a81ff3a13d2716395b +size 18771247488 diff --git a/KAT-Dev.i1-Q5_K_M.gguf b/KAT-Dev.i1-Q5_K_M.gguf new file mode 100644 index 0000000..74af0c4 --- /dev/null +++ b/KAT-Dev.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bdaf19df7d0c5e7380b8bff705ba44e16ba7905ee48d6172ec57ba7ad2b9fac +size 23214834048 diff --git a/KAT-Dev.i1-Q5_K_S.gguf b/KAT-Dev.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8c340f3 --- /dev/null +++ b/KAT-Dev.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22e3534c5a92109cc8fa39d8b5e3920903cfaba67736c3aeacf101ae98c6687a +size 22635495808 diff --git a/KAT-Dev.i1-Q6_K.gguf b/KAT-Dev.i1-Q6_K.gguf new file mode 100644 index 0000000..9d0d959 --- /dev/null +++ b/KAT-Dev.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f61298da2acbea13a2cbdcd28cde61898879060a2ee400a37381157431fc2420 +size 26883308928 diff --git a/KAT-Dev.imatrix.gguf b/KAT-Dev.imatrix.gguf new file mode 100644 index 0000000..03bd04e --- /dev/null +++ b/KAT-Dev.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87989567dd09dd8c3a3c2dbc54d4a5569090d9056ec092ad5c59b18ff478d239 +size 15273216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..51f1551 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: Kwaipilot/KAT-Dev +language: +- multilingual +library_name: transformers +license: apache-2.0 +license_link: LICENSE +license_name: kwaipilot-license +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Kwaipilot/KAT-Dev + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KAT-Dev-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/KAT-Dev-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-Dev-i1-GGUF/resolve/main/KAT-Dev.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ1_M.gguf) | i1-IQ1_M | 8.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ2_S.gguf) | i1-IQ2_S | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ2_M.gguf) | i1-IQ2_M | 11.5 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ3_M.gguf) | i1-IQ3_M | 15.0 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.3 | | +| [GGUF](https://huggingface.co/mradermacher/KAT-Dev-i1-GGUF/resolve/main/KAT-Dev.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | 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. + +