commit 94655c63da95836494e42192ff5f8910ed4ab511 Author: ModelHub XC Date: Tue Jun 2 14:10:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepPrep-Qwen3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4840b79 --- /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 +DeepPrep-Qwen3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepPrep-Qwen3-8B.IQ4_XS.gguf b/DeepPrep-Qwen3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..fe682f5 --- /dev/null +++ b/DeepPrep-Qwen3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be0dec2d2fa57118b7a8342766005e4c8882a476498069b676396e4f83fa2e6 +size 4593296640 diff --git a/DeepPrep-Qwen3-8B.Q2_K.gguf b/DeepPrep-Qwen3-8B.Q2_K.gguf new file mode 100644 index 0000000..176b648 --- /dev/null +++ b/DeepPrep-Qwen3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281305d03296c3a1ac40d8c7d150e7eb7e8f0bdd14e2ff3a2b060acffa4bf932 +size 3281732864 diff --git a/DeepPrep-Qwen3-8B.Q3_K_L.gguf b/DeepPrep-Qwen3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..fda0233 --- /dev/null +++ b/DeepPrep-Qwen3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38f163daa3fe59f87e4f6334f276e789367939c6e9529168e94bdb648868a8fd +size 4431394048 diff --git a/DeepPrep-Qwen3-8B.Q3_K_M.gguf b/DeepPrep-Qwen3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..3c6902b --- /dev/null +++ b/DeepPrep-Qwen3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a0335a91e7683ab69bb322546a0fda8e8460ab02ace4068454b69be8d3f205 +size 4124161280 diff --git a/DeepPrep-Qwen3-8B.Q3_K_S.gguf b/DeepPrep-Qwen3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..5005819 --- /dev/null +++ b/DeepPrep-Qwen3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dab1fefd2e2b4b75ce4df7f60927535915578f9f7a29b698605abff132e03af +size 3769611520 diff --git a/DeepPrep-Qwen3-8B.Q4_K_M.gguf b/DeepPrep-Qwen3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..1208466 --- /dev/null +++ b/DeepPrep-Qwen3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e50d81630eee527558da49505ced51ae41d47de53fb11c8cc3881c2680b22aa3 +size 5027783936 diff --git a/DeepPrep-Qwen3-8B.Q4_K_S.gguf b/DeepPrep-Qwen3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..833d65a --- /dev/null +++ b/DeepPrep-Qwen3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba9626a4b9d571e3591b4fb87dc786f2cd47374f42938150ad567b6f98b5a6ed +size 4802012416 diff --git a/DeepPrep-Qwen3-8B.Q5_K_M.gguf b/DeepPrep-Qwen3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..6288248 --- /dev/null +++ b/DeepPrep-Qwen3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade4f3fc008102ce2941d08490c93024d3d2866904495c93c0f67bae452029c3 +size 5851112704 diff --git a/DeepPrep-Qwen3-8B.Q5_K_S.gguf b/DeepPrep-Qwen3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..4aa1e81 --- /dev/null +++ b/DeepPrep-Qwen3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:812634c4419d45d457c2873e0490f290b5a1863b7989c414e0c3aeb4d3c0d621 +size 5720761600 diff --git a/DeepPrep-Qwen3-8B.Q6_K.gguf b/DeepPrep-Qwen3-8B.Q6_K.gguf new file mode 100644 index 0000000..65903c4 --- /dev/null +++ b/DeepPrep-Qwen3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2b6cac03991b777236a563514f5fea1f2d3dc8ab1efc965e8aede52ba35578a +size 6725899520 diff --git a/DeepPrep-Qwen3-8B.Q8_0.gguf b/DeepPrep-Qwen3-8B.Q8_0.gguf new file mode 100644 index 0000000..6e5a1f2 --- /dev/null +++ b/DeepPrep-Qwen3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb6f78aa7fbda2866d57346fdf0e7c8c607cbdc97cf04db7a90a7a8c15fff75 +size 8709518592 diff --git a/DeepPrep-Qwen3-8B.f16.gguf b/DeepPrep-Qwen3-8B.f16.gguf new file mode 100644 index 0000000..d7e376e --- /dev/null +++ b/DeepPrep-Qwen3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6315241c43ba7fcfee6a4343eaa290653df27fa732295ecb43c3aa1ebe8c2c52 +size 16388044032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2f76677 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: DeepPrep/DeepPrep-Qwen3-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DeepPrep/DeepPrep-Qwen3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepPrep-Qwen3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-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/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-8B-GGUF/resolve/main/DeepPrep-Qwen3-8B.f16.gguf) | f16 | 16.5 | 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. + +