commit dd18f786ac841384414f17be32e8569e0828d8e0 Author: ModelHub XC Date: Sun Jun 14 08:16:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/kaidol-thinking-sft-4b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..acfe587 --- /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 +kaidol-thinking-sft-4b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +kaidol-thinking-sft-4b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ecd278e --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: developer-lunark/kaidol-thinking-sft-4b +language: +- ko +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- kaidol +- chatbot +- idol +- thinking +- qwen +- lora +--- +## About + + + + + + + + + +static quants of https://huggingface.co/developer-lunark/kaidol-thinking-sft-4b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#kaidol-thinking-sft-4b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-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/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/kaidol-thinking-sft-4b-GGUF/resolve/main/kaidol-thinking-sft-4b.f16.gguf) | f16 | 8.9 | 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/kaidol-thinking-sft-4b.IQ4_XS.gguf b/kaidol-thinking-sft-4b.IQ4_XS.gguf new file mode 100644 index 0000000..1afc838 --- /dev/null +++ b/kaidol-thinking-sft-4b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df7d02f1d133d4be30d01b8f812c060b6df17424f25ea466beee4019862dbadf +size 2492019840 diff --git a/kaidol-thinking-sft-4b.Q2_K.gguf b/kaidol-thinking-sft-4b.Q2_K.gguf new file mode 100644 index 0000000..d43e4fe --- /dev/null +++ b/kaidol-thinking-sft-4b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3395bed28d651d485f5347b21d66c5a2445c9d6a4f81d8bd029a541eb9adbc76 +size 1796335328 diff --git a/kaidol-thinking-sft-4b.Q3_K_L.gguf b/kaidol-thinking-sft-4b.Q3_K_L.gguf new file mode 100644 index 0000000..935eee9 --- /dev/null +++ b/kaidol-thinking-sft-4b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb3e8ae36439f25450618e6339344bfb16073f217d527a453f1a6f1e6eaa6a23 +size 2406055328 diff --git a/kaidol-thinking-sft-4b.Q3_K_M.gguf b/kaidol-thinking-sft-4b.Q3_K_M.gguf new file mode 100644 index 0000000..702fd71 --- /dev/null +++ b/kaidol-thinking-sft-4b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df92872dfffc0e953e97ba7a828916a74ff832a78bf4731c434a377d44d9dda5 +size 2241887648 diff --git a/kaidol-thinking-sft-4b.Q3_K_S.gguf b/kaidol-thinking-sft-4b.Q3_K_S.gguf new file mode 100644 index 0000000..ab9276c --- /dev/null +++ b/kaidol-thinking-sft-4b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a1438bd506b50fef6ad548d5e12aec93b252694c6cfe3b19daa2efbbd7a791 +size 2053266848 diff --git a/kaidol-thinking-sft-4b.Q4_K_M.gguf b/kaidol-thinking-sft-4b.Q4_K_M.gguf new file mode 100644 index 0000000..e311583 --- /dev/null +++ b/kaidol-thinking-sft-4b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff7c9259372536036492a019f4c7240666c895e17763e1b7a62cec5350a73de +size 2715117824 diff --git a/kaidol-thinking-sft-4b.Q4_K_S.gguf b/kaidol-thinking-sft-4b.Q4_K_S.gguf new file mode 100644 index 0000000..e0af22f --- /dev/null +++ b/kaidol-thinking-sft-4b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f814019915cb298b22ae58efbfbe0e9a6c2f0242d0c1ad82b282ba57d075deb +size 2601146624 diff --git a/kaidol-thinking-sft-4b.Q5_K_M.gguf b/kaidol-thinking-sft-4b.Q5_K_M.gguf new file mode 100644 index 0000000..ec9d021 --- /dev/null +++ b/kaidol-thinking-sft-4b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1bdde5f5e3656fdc929a5ca979b633aa4fca1e8730fee5d34f77b41797906c8 +size 3155884864 diff --git a/kaidol-thinking-sft-4b.Q5_K_S.gguf b/kaidol-thinking-sft-4b.Q5_K_S.gguf new file mode 100644 index 0000000..b320228 --- /dev/null +++ b/kaidol-thinking-sft-4b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:901ce6f3575c0662c9ae759d890d953eaecb8245bcf8eea071b800177a6c046b +size 3090082624 diff --git a/kaidol-thinking-sft-4b.Q6_K.gguf b/kaidol-thinking-sft-4b.Q6_K.gguf new file mode 100644 index 0000000..2d097c2 --- /dev/null +++ b/kaidol-thinking-sft-4b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23badd8d9bea78442c9cbc22edbe6e5f1b0b5a495fdd50b3e4f20cc0087b48e1 +size 3624199872 diff --git a/kaidol-thinking-sft-4b.Q8_0.gguf b/kaidol-thinking-sft-4b.Q8_0.gguf new file mode 100644 index 0000000..f95dfaa --- /dev/null +++ b/kaidol-thinking-sft-4b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9333d4501c3d5a162cf42a1d4e7852191ffa8d38342379f441b032b0bb9d35 +size 4692213056 diff --git a/kaidol-thinking-sft-4b.f16.gguf b/kaidol-thinking-sft-4b.f16.gguf new file mode 100644 index 0000000..e6b1ecf --- /dev/null +++ b/kaidol-thinking-sft-4b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28343fbed69ee0dbd573442205f9c91551bc04608630c47aa4e797e40e0ba5ba +size 8826457856