commit d7de72020a71f2b7a6678dc0389e460b30858718 Author: ModelHub XC Date: Fri Jul 10 05:13:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepPrep-Qwen2.5-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..29ff52c --- /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-Qwen2.5-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen2.5-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepPrep-Qwen2.5-3B.IQ4_XS.gguf b/DeepPrep-Qwen2.5-3B.IQ4_XS.gguf new file mode 100644 index 0000000..c019c36 --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c98396ae06e3ad81505096d0a09cfc40f22f81b3f31d1b39523cb160aac35aad +size 1918491456 diff --git a/DeepPrep-Qwen2.5-3B.Q2_K.gguf b/DeepPrep-Qwen2.5-3B.Q2_K.gguf new file mode 100644 index 0000000..f4a61e7 --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02682050426e4094554201bf2e0c5addcca244f84e014e55019c8f4b7dace946 +size 1376856896 diff --git a/DeepPrep-Qwen2.5-3B.Q3_K_L.gguf b/DeepPrep-Qwen2.5-3B.Q3_K_L.gguf new file mode 100644 index 0000000..afa172d --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b46cb53e38fb606e8e9544ba61eb77acf83cf62556e300183fce3ddf5ca0e1 +size 1841095488 diff --git a/DeepPrep-Qwen2.5-3B.Q3_K_M.gguf b/DeepPrep-Qwen2.5-3B.Q3_K_M.gguf new file mode 100644 index 0000000..4906c22 --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6d1e816a2ab8bee620e877b360d98913d6fd2bcd43b3d40dfd3a9f6a5ebaf85 +size 1724179264 diff --git a/DeepPrep-Qwen2.5-3B.Q3_K_S.gguf b/DeepPrep-Qwen2.5-3B.Q3_K_S.gguf new file mode 100644 index 0000000..6519ff4 --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1428303278bd597f5414bd8c81180245660d1f002feb1ce84cf89f204ee9bd59 +size 1588060992 diff --git a/DeepPrep-Qwen2.5-3B.Q4_K_M.gguf b/DeepPrep-Qwen2.5-3B.Q4_K_M.gguf new file mode 100644 index 0000000..05b15fe --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24712776c1fba0f2df4f02488ec3dc8dd0bbd4eafe64b354646fe741b081f6d4 +size 2104933184 diff --git a/DeepPrep-Qwen2.5-3B.Q4_K_S.gguf b/DeepPrep-Qwen2.5-3B.Q4_K_S.gguf new file mode 100644 index 0000000..3382ce4 --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6059def7c51c17719c3c609a40a86f0c0e8aaa495366ae265fa63dc90bc6a107 +size 2009414464 diff --git a/DeepPrep-Qwen2.5-3B.Q5_K_M.gguf b/DeepPrep-Qwen2.5-3B.Q5_K_M.gguf new file mode 100644 index 0000000..d210612 --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228d12378bffcd2ad409976c2038b6e07eee277f08f1e403017b77e8936c5fb1 +size 2438740800 diff --git a/DeepPrep-Qwen2.5-3B.Q5_K_S.gguf b/DeepPrep-Qwen2.5-3B.Q5_K_S.gguf new file mode 100644 index 0000000..254fa35 --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f87a72747a0aea6b95649269851ef75da27c7ed5cd476a5c613052cf58904a4 +size 2383592256 diff --git a/DeepPrep-Qwen2.5-3B.Q6_K.gguf b/DeepPrep-Qwen2.5-3B.Q6_K.gguf new file mode 100644 index 0000000..8649a42 --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2288d46fca2601c177c96da61fd01b29e135722cfd8b9fbb27cdef44265e3c7b +size 2793411392 diff --git a/DeepPrep-Qwen2.5-3B.Q8_0.gguf b/DeepPrep-Qwen2.5-3B.Q8_0.gguf new file mode 100644 index 0000000..24b190a --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b595f2502e4d42abc3d1f8b42bbeb24f7abc26e8da522fed1ce1566d320fa79 +size 3616088896 diff --git a/DeepPrep-Qwen2.5-3B.f16.gguf b/DeepPrep-Qwen2.5-3B.f16.gguf new file mode 100644 index 0000000..6c749e2 --- /dev/null +++ b/DeepPrep-Qwen2.5-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:302d0b962c168463fe3796f44e6dcf95dd39e6970926390fc3d31ada3f96fc5a +size 6800646976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5191912 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: DeepPrep/DeepPrep-Qwen2.5-3B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DeepPrep/DeepPrep-Qwen2.5-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepPrep-Qwen2.5-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-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-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen2.5-3B-GGUF/resolve/main/DeepPrep-Qwen2.5-3B.f16.gguf) | f16 | 6.9 | 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. + +