commit 92712b7abebffa2c5c2d8531b0a9e4d952437114 Author: ModelHub XC Date: Sat Aug 8 16:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dba1e9f --- /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-CreativeWriting-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-CreativeWriting-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-CreativeWriting-SFT.IQ4_XS.gguf b/Qwen3-4B-CreativeWriting-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..0eb0e89 --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4baca5105626ecabde7a11fd42e0381cc57827d846d029f69b35d16fea6f55c4 +size 2492947904 diff --git a/Qwen3-4B-CreativeWriting-SFT.Q2_K.gguf b/Qwen3-4B-CreativeWriting-SFT.Q2_K.gguf new file mode 100644 index 0000000..5b18f64 --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e55159b2b0553f1013c316e69ce6426f8bd5eb3cc94b5ba98a435628eebc4d +size 1797124544 diff --git a/Qwen3-4B-CreativeWriting-SFT.Q3_K_L.gguf b/Qwen3-4B-CreativeWriting-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..6871ba1 --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828885e214f01f7a36f9f1382f0785c43f1b32ced8087daaf5da995d7cfc4720 +size 2406913984 diff --git a/Qwen3-4B-CreativeWriting-SFT.Q3_K_M.gguf b/Qwen3-4B-CreativeWriting-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..0b44c7e --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9c36efa45007c106fc9798093eb2225f8f64f8278ed2b20f1328b506c1ed8dc +size 2242746304 diff --git a/Qwen3-4B-CreativeWriting-SFT.Q3_K_S.gguf b/Qwen3-4B-CreativeWriting-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..c325f9d --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14590f52eb63f7b8317df87845d6649bf223634a3d970801df45668ced8eb382 +size 2054125504 diff --git a/Qwen3-4B-CreativeWriting-SFT.Q4_K_M.gguf b/Qwen3-4B-CreativeWriting-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..ff38a04 --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25db1a14b3aee7f4f1cb3fde230705d44f0870c357ba36d506ab3a8e119d57d0 +size 2716067264 diff --git a/Qwen3-4B-CreativeWriting-SFT.Q4_K_S.gguf b/Qwen3-4B-CreativeWriting-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..dcf923c --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ebaa7a70f8a37a968ac4f0a7625b33a6c68c6e83a2236014914d7d188a63d95 +size 2602096064 diff --git a/Qwen3-4B-CreativeWriting-SFT.Q5_K_M.gguf b/Qwen3-4B-CreativeWriting-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..78801c5 --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:895e381440c912f7210c077fee541bf82900dafb0e457a6fca9d3421a6eee3aa +size 3156919744 diff --git a/Qwen3-4B-CreativeWriting-SFT.Q5_K_S.gguf b/Qwen3-4B-CreativeWriting-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..d6912a5 --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3d538e7b7955c79e14b257a3256736a1c786468d815eb5a874fccd325364332 +size 3091117504 diff --git a/Qwen3-4B-CreativeWriting-SFT.Q6_K.gguf b/Qwen3-4B-CreativeWriting-SFT.Q6_K.gguf new file mode 100644 index 0000000..7674a84 --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4958fcdd726c96f2e5ff13e10ce794be4edad181044ae0212fedd44e263ccc6 +size 3625325504 diff --git a/Qwen3-4B-CreativeWriting-SFT.Q8_0.gguf b/Qwen3-4B-CreativeWriting-SFT.Q8_0.gguf new file mode 100644 index 0000000..0eba388 --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3add404800ea9c6f0a9231b06145f548381a9f36770754e46f1d12d7dcf7c144 +size 4693669824 diff --git a/Qwen3-4B-CreativeWriting-SFT.f16.gguf b/Qwen3-4B-CreativeWriting-SFT.f16.gguf new file mode 100644 index 0000000..2931a01 --- /dev/null +++ b/Qwen3-4B-CreativeWriting-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df108ad7da46c1d79d1feec597a39a3f4b04ffafdb2f7389fa2f3a595530ccfb +size 8829196224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..168fc86 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: bowen-upenn/Qwen3-4B-CreativeWriting-SFT +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/bowen-upenn/Qwen3-4B-CreativeWriting-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-CreativeWriting-SFT-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-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-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-CreativeWriting-SFT-GGUF/resolve/main/Qwen3-4B-CreativeWriting-SFT.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. + +