commit bee40077bed4d60047d415be763d3ca15ca57f9f Author: ModelHub XC Date: Tue Jun 30 10:46:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KAFKA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..aa43ab4 --- /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 +KAFKA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KAFKA.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KAFKA.IQ4_XS.gguf b/KAFKA.IQ4_XS.gguf new file mode 100644 index 0000000..88b9865 --- /dev/null +++ b/KAFKA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30474a5fd16ce06aa283b33870f542deee0ce42ab5a502dad5055e1163d7e7d9 +size 750722592 diff --git a/KAFKA.Q2_K.gguf b/KAFKA.Q2_K.gguf new file mode 100644 index 0000000..86bccac --- /dev/null +++ b/KAFKA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2fbd1ca510841d26e9cffe289632299b706126f5e515e6f72f7488754dd9d7f +size 559717920 diff --git a/KAFKA.Q3_K_L.gguf b/KAFKA.Q3_K_L.gguf new file mode 100644 index 0000000..ab6b84a --- /dev/null +++ b/KAFKA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:552ca0cd75281195460a432c687537219ec006e5458f2678cedb59b17e6b9d7e +size 744455712 diff --git a/KAFKA.Q3_K_M.gguf b/KAFKA.Q3_K_M.gguf new file mode 100644 index 0000000..ec62ca8 --- /dev/null +++ b/KAFKA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e92c85dab37769ed770fb3c1ff08509f50937f39caf9915b335b69931daddd5 +size 704134688 diff --git a/KAFKA.Q3_K_S.gguf b/KAFKA.Q3_K_S.gguf new file mode 100644 index 0000000..7219937 --- /dev/null +++ b/KAFKA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e4318fcc80e2e3f223835de6a03a4e01166d57278dbeb0afc70bc709b21d7d3 +size 641826336 diff --git a/KAFKA.Q4_K_M.gguf b/KAFKA.Q4_K_M.gguf new file mode 100644 index 0000000..84e3f35 --- /dev/null +++ b/KAFKA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:080ba79a626ac423e534c755d78c07fd698a69c19b6355b3171c1e483de785cf +size 873455136 diff --git a/KAFKA.Q4_K_S.gguf b/KAFKA.Q4_K_S.gguf new file mode 100644 index 0000000..2398cf3 --- /dev/null +++ b/KAFKA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84b1ee46c7d40ef528ff8e184085028dda56ad953d3167c131c9247d8f66f639 +size 813964832 diff --git a/KAFKA.Q5_K_M.gguf b/KAFKA.Q5_K_M.gguf new file mode 100644 index 0000000..4ca96c9 --- /dev/null +++ b/KAFKA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2dda97df89a0010d687dac3628d8a85a18c3183558159febf9a545abfb61cbe +size 1001840160 diff --git a/KAFKA.Q5_K_S.gguf b/KAFKA.Q5_K_S.gguf new file mode 100644 index 0000000..bf2c958 --- /dev/null +++ b/KAFKA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41e34ed47057c6ddbe90e30144604037414b4cea739e38737e7fa4bc59798d74 +size 952884768 diff --git a/KAFKA.Q6_K.gguf b/KAFKA.Q6_K.gguf new file mode 100644 index 0000000..58fef62 --- /dev/null +++ b/KAFKA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f2d9d1270bbbdbe7cbe8b0fe457dea8b5b9d204091dd60b2c8df6bf5489196 +size 1171537440 diff --git a/KAFKA.Q8_0.gguf b/KAFKA.Q8_0.gguf new file mode 100644 index 0000000..c2f0829 --- /dev/null +++ b/KAFKA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:777029da14d76ce7a49dafe7031fa6e267c45a491ac4b8a798df5315933cd8be +size 1432092192 diff --git a/KAFKA.f16.gguf b/KAFKA.f16.gguf new file mode 100644 index 0000000..5c0977b --- /dev/null +++ b/KAFKA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2994aef452b095c1fad8b5f980618c33272a9b8152b87822ecf3099eeef29ed +size 2694315552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ebd0f08 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: abdo2020/KAFKA +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/abdo2020/KAFKA + + +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/KAFKA-GGUF/resolve/main/KAFKA.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.IQ4_XS.gguf) | IQ4_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.Q5_K_S.gguf) | Q5_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.Q5_K_M.gguf) | Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.Q8_0.gguf) | Q8_0 | 1.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KAFKA-GGUF/resolve/main/KAFKA.f16.gguf) | f16 | 2.8 | 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. + +