commit 16fcf230a33a2c77826c41aae8691413051c5b0d Author: ModelHub XC Date: Thu Oct 15 13:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6e24a3d --- /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 +Korean-Qwen3-4B-Thinking-2507-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Korean-Qwen3-4B-Thinking-2507-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.IQ4_XS.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.IQ4_XS.gguf new file mode 100644 index 0000000..699c47f --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0026521e74a24e53a1a14fcb7b44c6e783d23fc36e731dc5c9ea13ddfdc748d0 +size 2286316736 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.Q2_K.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.Q2_K.gguf new file mode 100644 index 0000000..b357778 --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:021eec106559c810a7c9b730064ef6c5029e66a53759326eb33302730c52b4b4 +size 1669500096 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_L.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_L.gguf new file mode 100644 index 0000000..c6ffab2 --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43f2e5dc718c6807331e45dce8d888403412af088847e8d48202768ab8227971 +size 2239786176 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_M.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_M.gguf new file mode 100644 index 0000000..f2fd1d1 --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d76f56c8deaa3c44b0b11f17fe7f7e6f32ac9b643a1ec6cdfa9a1cbba4ebac +size 2075618496 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_S.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_S.gguf new file mode 100644 index 0000000..bcdd20e --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0de4ffffd1fadfdbb96224f1074e47c6ca1bc1e98d186734e389052d6f2acab +size 1886997696 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.Q4_K_M.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.Q4_K_M.gguf new file mode 100644 index 0000000..6c3ded0 --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a7b4008c0587ed566fa14ebe8eef8424acaeb3125bd42e8b7bf229e9a12ff8 +size 2497281216 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.Q4_K_S.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.Q4_K_S.gguf new file mode 100644 index 0000000..d3539b4 --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e05c79df61b8ca27b6c951c9fbece34c8443b6dfa33397a8a79b9aa14c229d2c +size 2383310016 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.Q5_K_M.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.Q5_K_M.gguf new file mode 100644 index 0000000..0db03ee --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf450d1dc8baec7ed0a054a38996172ddab67f19fab691cae087906d69249e94 +size 2889514176 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.Q5_K_S.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.Q5_K_S.gguf new file mode 100644 index 0000000..ce72085 --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d86a7f7d9173a8b01cd8f811c5d371a591a7012637fb620b993a53c2f93abde +size 2823711936 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.Q6_K.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.Q6_K.gguf new file mode 100644 index 0000000..2634de2 --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a28ed80cec087b2e9d2ff2ff7b20bac8fabcd67d4109de39ea922ff1f8468f89 +size 3306261696 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.Q8_0.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.Q8_0.gguf new file mode 100644 index 0000000..f03f6f0 --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e9bf7d096b679798524633d2ec0306f13ef3c27fa580c70fca01bd8a7c0027 +size 4280405696 diff --git a/Korean-Qwen3-4B-Thinking-2507-sft.f16.gguf b/Korean-Qwen3-4B-Thinking-2507-sft.f16.gguf new file mode 100644 index 0000000..8aa5761 --- /dev/null +++ b/Korean-Qwen3-4B-Thinking-2507-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be98e285eac0c3485141ea008e5f37f0100cb0f7df83b1171d41b59e27809b4a +size 8051285696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b58c140 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Jackrong/Korean-Qwen3-4B-Thinking-2507-sft +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jackrong/Korean-Qwen3-4B-Thinking-2507-sft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Korean-Qwen3-4B-Thinking-2507-sft-GGUF).*** + +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/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Korean-Qwen3-4B-Thinking-2507-sft-GGUF/resolve/main/Korean-Qwen3-4B-Thinking-2507-sft.f16.gguf) | f16 | 8.2 | 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. + +