commit 58ee383705cc189b9f96553e8af31eeec618ab00 Author: ModelHub XC Date: Mon Sep 14 02:02:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..26055b4 --- /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-SFT2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-DeepWriting-SFT2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-DeepWriting-SFT2.IQ4_XS.gguf b/Qwen3-4B-DeepWriting-SFT2.IQ4_XS.gguf new file mode 100644 index 0000000..7112a8c --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c46e00149498731ed35bb909b331f97682ae0004c4805f4989dbb8a386f659 +size 2286316512 diff --git a/Qwen3-4B-DeepWriting-SFT2.Q2_K.gguf b/Qwen3-4B-DeepWriting-SFT2.Q2_K.gguf new file mode 100644 index 0000000..7f19221 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8435c2b9a7e045af0509b12165dab3941a1555aa95fd3815c30d358f62ce1b2c +size 1669499872 diff --git a/Qwen3-4B-DeepWriting-SFT2.Q3_K_L.gguf b/Qwen3-4B-DeepWriting-SFT2.Q3_K_L.gguf new file mode 100644 index 0000000..b0afcad --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06fe86646ab88efe1b8c55a1458f9514485f9bff7b9a9393d4e0071f27a24816 +size 2239785952 diff --git a/Qwen3-4B-DeepWriting-SFT2.Q3_K_M.gguf b/Qwen3-4B-DeepWriting-SFT2.Q3_K_M.gguf new file mode 100644 index 0000000..6f792e5 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e7d920eea40b092669ab52ba601c94f7bd407124f7195b9740d3ab750aebcf5 +size 2075618272 diff --git a/Qwen3-4B-DeepWriting-SFT2.Q3_K_S.gguf b/Qwen3-4B-DeepWriting-SFT2.Q3_K_S.gguf new file mode 100644 index 0000000..f00f4df --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ca0f3467828225ed95fcc146c96c7bd9f00c71f2bd692d293ada260587f56d +size 1886997472 diff --git a/Qwen3-4B-DeepWriting-SFT2.Q4_K_M.gguf b/Qwen3-4B-DeepWriting-SFT2.Q4_K_M.gguf new file mode 100644 index 0000000..42df4e2 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12e4618f378007e285780dee31e83d1bfb2342d4fbf053c7ab9ec56a25779109 +size 2497280992 diff --git a/Qwen3-4B-DeepWriting-SFT2.Q4_K_S.gguf b/Qwen3-4B-DeepWriting-SFT2.Q4_K_S.gguf new file mode 100644 index 0000000..2c7a10d --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28dcc5d446c2999d0b517b0a556fefb43234934e4ffdc4f2e05e70dd51e26a3a +size 2383309792 diff --git a/Qwen3-4B-DeepWriting-SFT2.Q5_K_M.gguf b/Qwen3-4B-DeepWriting-SFT2.Q5_K_M.gguf new file mode 100644 index 0000000..30bc9d3 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e575f598f194bb5733b349da4b44401d4d5141e80e4301485008854d462a45 +size 2889513952 diff --git a/Qwen3-4B-DeepWriting-SFT2.Q5_K_S.gguf b/Qwen3-4B-DeepWriting-SFT2.Q5_K_S.gguf new file mode 100644 index 0000000..cd66d6d --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e14f3898ecf2a37c15d2376ec120e59f4bcbcf733f0e4925d29e37e6dd7947b4 +size 2823711712 diff --git a/Qwen3-4B-DeepWriting-SFT2.Q6_K.gguf b/Qwen3-4B-DeepWriting-SFT2.Q6_K.gguf new file mode 100644 index 0000000..33ea517 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5f35f9e631f5931aa32cd051d4f91874fa8aad9cb5bb19bbed2ee993b23d9be +size 3306261472 diff --git a/Qwen3-4B-DeepWriting-SFT2.Q8_0.gguf b/Qwen3-4B-DeepWriting-SFT2.Q8_0.gguf new file mode 100644 index 0000000..3457b45 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13237a7309c7b36169bd6390c517ebb19d6901126c6e2d3f18330e14e825768d +size 4280405472 diff --git a/Qwen3-4B-DeepWriting-SFT2.f16.gguf b/Qwen3-4B-DeepWriting-SFT2.f16.gguf new file mode 100644 index 0000000..9e38784 --- /dev/null +++ b/Qwen3-4B-DeepWriting-SFT2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:797576d18354f3d61fd2ef226cae12cc8ccbfd5294b690ea22e4cd59d02c3fe5 +size 8051285472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ce9e501 --- /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-SFT2-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-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-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-DeepWriting-SFT2-GGUF/resolve/main/Qwen3-4B-DeepWriting-SFT2.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. + +