commit ab63f7709144d4726f2a2adbed4e159d14eb0e64 Author: ModelHub XC Date: Sun May 10 09:34:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Cute_Experiment-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a941424 --- /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 +Cute_Experiment-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cute_Experiment-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Cute_Experiment-8B.IQ4_XS.gguf b/Cute_Experiment-8B.IQ4_XS.gguf new file mode 100644 index 0000000..9b7d12a --- /dev/null +++ b/Cute_Experiment-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6729f7ca47a3bb0b6caf05723c338ef77626cc961d0fbebaefdcc47eb3c081c +size 4484368448 diff --git a/Cute_Experiment-8B.Q2_K.gguf b/Cute_Experiment-8B.Q2_K.gguf new file mode 100644 index 0000000..d7a19fc --- /dev/null +++ b/Cute_Experiment-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:178258d47dcbd7305576a2312178bdca0d471c2530a938387666eea950762154 +size 3179137088 diff --git a/Cute_Experiment-8B.Q3_K_L.gguf b/Cute_Experiment-8B.Q3_K_L.gguf new file mode 100644 index 0000000..24540e5 --- /dev/null +++ b/Cute_Experiment-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cf9a8542ee07452661ae1a23ef6e5b7a471d256594a0adbbe8261f858372ad5 +size 4321962048 diff --git a/Cute_Experiment-8B.Q3_K_M.gguf b/Cute_Experiment-8B.Q3_K_M.gguf new file mode 100644 index 0000000..2ba01e4 --- /dev/null +++ b/Cute_Experiment-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a07d0a3fe3506c6ce7aa66a5b0f25aa69913ae8909afd639df55758564fbfa20 +size 4018923584 diff --git a/Cute_Experiment-8B.Q3_K_S.gguf b/Cute_Experiment-8B.Q3_K_S.gguf new file mode 100644 index 0000000..0e15f6c --- /dev/null +++ b/Cute_Experiment-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:038bcc7fb53685d92499f964adb81597f37810afaab490632af52a9bf46af008 +size 3664504896 diff --git a/Cute_Experiment-8B.Q4_K_M.gguf b/Cute_Experiment-8B.Q4_K_M.gguf new file mode 100644 index 0000000..f71e89b --- /dev/null +++ b/Cute_Experiment-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64c7afb3c6341d2c9c5d6c0ccea58aa584856fd922d97800a03168ab2e510ee6 +size 4920739904 diff --git a/Cute_Experiment-8B.Q4_K_S.gguf b/Cute_Experiment-8B.Q4_K_S.gguf new file mode 100644 index 0000000..4e24903 --- /dev/null +++ b/Cute_Experiment-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ea03f10cb6bfc8459eed8c90677f802b1dac8cf22edab8384efdbcdcf8fc049 +size 4692674624 diff --git a/Cute_Experiment-8B.Q5_K_M.gguf b/Cute_Experiment-8B.Q5_K_M.gguf new file mode 100644 index 0000000..c852601 --- /dev/null +++ b/Cute_Experiment-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9470c32671359091de7c27a8665661bd8e33c71e33bab4d707219416061581 +size 5732993088 diff --git a/Cute_Experiment-8B.Q5_K_S.gguf b/Cute_Experiment-8B.Q5_K_S.gguf new file mode 100644 index 0000000..667aa8c --- /dev/null +++ b/Cute_Experiment-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2048765592f67403ad4adc1e0a4926c82fabd6d265cc092aea32615631305fc +size 5599299648 diff --git a/Cute_Experiment-8B.Q6_K.gguf b/Cute_Experiment-8B.Q6_K.gguf new file mode 100644 index 0000000..79813c1 --- /dev/null +++ b/Cute_Experiment-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d80b7871aca89bac26ece94bb91e9feb897a7e3a3f2c4900f6717dd9855f5a +size 6596012096 diff --git a/Cute_Experiment-8B.Q8_0.gguf b/Cute_Experiment-8B.Q8_0.gguf new file mode 100644 index 0000000..efcbf4e --- /dev/null +++ b/Cute_Experiment-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3874ba35ad8de86e9e87b3c73d67a3a10ce4f9cc5438693d22e37894cec9fa54 +size 8540776512 diff --git a/Cute_Experiment-8B.f16.gguf b/Cute_Experiment-8B.f16.gguf new file mode 100644 index 0000000..0744346 --- /dev/null +++ b/Cute_Experiment-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d6ab3835abcd0beba92feaed1dcee211e6dffa2bf2b5011cc013d74feb05908 +size 16068896832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..673fbc1 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: mergekit-community/Cute_Experiment-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mergekit-community/Cute_Experiment-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Cute_Experiment-8B-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/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Cute_Experiment-8B-GGUF/resolve/main/Cute_Experiment-8B.f16.gguf) | f16 | 16.2 | 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. + +