commit 2d48293c8d9da61ff0c69f7b11da1e780ed59072 Author: ModelHub XC Date: Mon Sep 14 13:10:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..065f622 --- /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 +Qwen3-4B-DeepWriting-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-DeepWriting-SFT.IQ4_XS.gguf b/Qwen3-4B-DeepWriting-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..30a9bb6 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:094491d9e22cf326d828e09152991b235b8f570f57c3665284125c572d4aa764 +size 2286316512 diff --git a/Qwen3-4B-DeepWriting-SFT.Q2_K.gguf b/Qwen3-4B-DeepWriting-SFT.Q2_K.gguf new file mode 100644 index 0000000..71cd820 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8989fc5054ab3917cc2360e45816ea27eca3e0238f06aa7e8425eb2c261dee41 +size 1669499872 diff --git a/Qwen3-4B-DeepWriting-SFT.Q3_K_L.gguf b/Qwen3-4B-DeepWriting-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..7429754 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06aa048bc40684a5a2983da3791f44c6a56e4aad93e0880fa24e2047fea8cc4a +size 2239785952 diff --git a/Qwen3-4B-DeepWriting-SFT.Q3_K_M.gguf b/Qwen3-4B-DeepWriting-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..f3837a8 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e4ebfce1817e908c3537afd68328c6ef1a28612f346f8f86df66c0db9f4903 +size 2075618272 diff --git a/Qwen3-4B-DeepWriting-SFT.Q3_K_S.gguf b/Qwen3-4B-DeepWriting-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..f26e849 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be6c5971829c5e2c81fb7abb66b485de85a3be32561e56d66361e30ec3f372ca +size 1886997472 diff --git a/Qwen3-4B-DeepWriting-SFT.Q4_K_M.gguf b/Qwen3-4B-DeepWriting-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..95d81f0 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66d5ddcbe8cdaa8f1fa9ca50dc6dcfbcb2c864fd1ab89424d183da9b891878e2 +size 2497280992 diff --git a/Qwen3-4B-DeepWriting-SFT.Q4_K_S.gguf b/Qwen3-4B-DeepWriting-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..43476ab --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc5bbd67b7f5753501050c195afef4c807b44c938d026cdeb0c4dc2c7b4652e8 +size 2383309792 diff --git a/Qwen3-4B-DeepWriting-SFT.Q5_K_M.gguf b/Qwen3-4B-DeepWriting-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..12d52e3 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd6c99fe837d84a15d0958f80a6ca5ef7b63a1b515e83e045744ef60bb4a7fe +size 2889513952 diff --git a/Qwen3-4B-DeepWriting-SFT.Q5_K_S.gguf b/Qwen3-4B-DeepWriting-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..0e6af4b --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e28ffd0169b110b59ddad6bb3f2d0410b1c0c611e7e3625a1334707f14b880b +size 2823711712 diff --git a/Qwen3-4B-DeepWriting-SFT.Q6_K.gguf b/Qwen3-4B-DeepWriting-SFT.Q6_K.gguf new file mode 100644 index 0000000..166bd92 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64bed52ec576ebf4ea1934d6a59b60df0396f8f0f2d1d768b6eacc22d8fe40a6 +size 3306261472 diff --git a/Qwen3-4B-DeepWriting-SFT.Q8_0.gguf b/Qwen3-4B-DeepWriting-SFT.Q8_0.gguf new file mode 100644 index 0000000..c3b0ed9 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f941904d477c6eeebe325514f43089e0f371de002238e013582e0617a4ff3010 +size 4280405472 diff --git a/Qwen3-4B-DeepWriting-SFT.f16.gguf b/Qwen3-4B-DeepWriting-SFT.f16.gguf new file mode 100644 index 0000000..6ffda99 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b214d3ba0e1b614b1f569e90976b84b2d12826be13bb4d1d3aca0deaa75c428a +size 8051285472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7239004 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: ChuGyouk/Qwen3-4B-DeepWriting-SFT +language: +- en +library_name: transformers +model_name: Qwen3-4B-DeepWriting-SFT2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- sft +- unsloth +- trl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ChuGyouk/Qwen3-4B-DeepWriting-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-DeepWriting-SFT-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-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/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF/resolve/main/Qwen3-4B-DeepWriting-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. + +