commit dcfa56f876b0b2319255c7db4d3e349f31e58ac6 Author: ModelHub XC Date: Mon Sep 7 17:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/kukulemon-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..01608b2 --- /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 +kukulemon-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +kukulemon-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7873a30 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: grimjim/kukulemon-7B +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/grimjim/kukulemon-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/kukulemon-7B-i1-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/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.f16.gguf) | f16 | 14.6 | 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. + + diff --git a/kukulemon-7B.IQ4_XS.gguf b/kukulemon-7B.IQ4_XS.gguf new file mode 100644 index 0000000..ecf15ba --- /dev/null +++ b/kukulemon-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b05258be532e07643aa8e3c43015697d70633c44bdc7c408627fd0250136b6 +size 3944389728 diff --git a/kukulemon-7B.Q2_K.gguf b/kukulemon-7B.Q2_K.gguf new file mode 100644 index 0000000..9f972f0 --- /dev/null +++ b/kukulemon-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b3772638b02e9f5ced78f7217cff1d596fab2d70ccb9762cf79b5991756722f +size 2719243360 diff --git a/kukulemon-7B.Q3_K_L.gguf b/kukulemon-7B.Q3_K_L.gguf new file mode 100644 index 0000000..bca4b81 --- /dev/null +++ b/kukulemon-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c81ed7951c615cf1ee0ac52590e5a7b2695c7dffb312ccb4c5ac7beda64a315 +size 3822025824 diff --git a/kukulemon-7B.Q3_K_M.gguf b/kukulemon-7B.Q3_K_M.gguf new file mode 100644 index 0000000..9972862 --- /dev/null +++ b/kukulemon-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c1739db65c39d20453005608423c1af162a4c21036f1bb9cae7ce704c1bbe2 +size 3518987360 diff --git a/kukulemon-7B.Q3_K_S.gguf b/kukulemon-7B.Q3_K_S.gguf new file mode 100644 index 0000000..a843149 --- /dev/null +++ b/kukulemon-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0dd8b6a9a48de71e75feb45a543aba696a38d9debe9f5ae65bc0d8832ca9191 +size 3164568672 diff --git a/kukulemon-7B.Q4_K_M.gguf b/kukulemon-7B.Q4_K_M.gguf new file mode 100644 index 0000000..d352919 --- /dev/null +++ b/kukulemon-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f61c7152e4ef588042a113cc3c37d087eb88c8ccb87fa6f9027ae7c0321ce5a +size 4368440416 diff --git a/kukulemon-7B.Q4_K_S.gguf b/kukulemon-7B.Q4_K_S.gguf new file mode 100644 index 0000000..3b9f59a --- /dev/null +++ b/kukulemon-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad025ec528355694cf8b04002d2a685e914af812a02e41e76ba95f7a5082b028 +size 4140375136 diff --git a/kukulemon-7B.Q5_K_M.gguf b/kukulemon-7B.Q5_K_M.gguf new file mode 100644 index 0000000..6c7d26e --- /dev/null +++ b/kukulemon-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be7bec63aa79808667a26b1e3c032c98410bffe742b6a5cd9ba28a1503d80578 +size 5131410528 diff --git a/kukulemon-7B.Q5_K_S.gguf b/kukulemon-7B.Q5_K_S.gguf new file mode 100644 index 0000000..fb56e77 --- /dev/null +++ b/kukulemon-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b513775d318344cc5446a04da0157ce8bbc95d44bb7fd63adc1adc6e464c1bc8 +size 4997717088 diff --git a/kukulemon-7B.Q6_K.gguf b/kukulemon-7B.Q6_K.gguf new file mode 100644 index 0000000..a6c6fe6 --- /dev/null +++ b/kukulemon-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac40eb4f2020488c15dabf5bff8e7009dc68b94a163deed92397aeacafbc925 +size 5942066272 diff --git a/kukulemon-7B.Q8_0.gguf b/kukulemon-7B.Q8_0.gguf new file mode 100644 index 0000000..f529dc7 --- /dev/null +++ b/kukulemon-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d21be7f39f71bb54d225fc17a972f926b1c8b4a2b6a229a53aeea61d3d771fe +size 7695858784 diff --git a/kukulemon-7B.f16.gguf b/kukulemon-7B.f16.gguf new file mode 100644 index 0000000..14a8640 --- /dev/null +++ b/kukulemon-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3df07620f3e9557446e901695466391e6170e6e5024d6b6d3b7ee0fbf52c44c +size 14484733024