commit acf28fef22d77a3a49979e3f0ee434f90a8f35a7 Author: ModelHub XC Date: Wed Jul 29 16:55:31 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepPrep-Qwen3-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..81b39da --- /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-Qwen3-0.6B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepPrep-Qwen3-0.6B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepPrep-Qwen3-0.6B.IQ4_XS.gguf b/DeepPrep-Qwen3-0.6B.IQ4_XS.gguf new file mode 100644 index 0000000..ce79962 --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049d5de4c855e2ae466c5fc3b387f72178ee641cdbe47a9b584dbf391ac09f79 +size 451931296 diff --git a/DeepPrep-Qwen3-0.6B.Q2_K.gguf b/DeepPrep-Qwen3-0.6B.Q2_K.gguf new file mode 100644 index 0000000..ab3d3c7 --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc781292d7c217ff802d01fca98732ff0ee3c0cdd6d8c11f4df7ec672bee5d5 +size 347288736 diff --git a/DeepPrep-Qwen3-0.6B.Q3_K_L.gguf b/DeepPrep-Qwen3-0.6B.Q3_K_L.gguf new file mode 100644 index 0000000..694f6d7 --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79bd7f70a8dc5a658e0bdee0c182613aac48f0598164b2d69e990cd9484f0dcf +size 435343520 diff --git a/DeepPrep-Qwen3-0.6B.Q3_K_M.gguf b/DeepPrep-Qwen3-0.6B.Q3_K_M.gguf new file mode 100644 index 0000000..d8ed991 --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49bafc2984f83fd8af64db0eb78d3b9977f3409460c4a1a610d93ef225578e45 +size 413978784 diff --git a/DeepPrep-Qwen3-0.6B.Q3_K_S.gguf b/DeepPrep-Qwen3-0.6B.Q3_K_S.gguf new file mode 100644 index 0000000..5c6ac30 --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d8102d486a5c8a35c9bfea8f9f1f12b763be60cd4ab23c8e531ff3783aeda5 +size 389927072 diff --git a/DeepPrep-Qwen3-0.6B.Q4_K_M.gguf b/DeepPrep-Qwen3-0.6B.Q4_K_M.gguf new file mode 100644 index 0000000..6b20d69 --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b45a44921b53e8eaff9f854e1e9f51d9de13b929076412c90737a35f8ebc0334 +size 484220064 diff --git a/DeepPrep-Qwen3-0.6B.Q4_K_S.gguf b/DeepPrep-Qwen3-0.6B.Q4_K_S.gguf new file mode 100644 index 0000000..fe3d64a --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa4199ca8f4d751c7a44886ff70cf3506a4b2ba913e5e7cc3e7840d8d5303d55 +size 470785184 diff --git a/DeepPrep-Qwen3-0.6B.Q5_K_M.gguf b/DeepPrep-Qwen3-0.6B.Q5_K_M.gguf new file mode 100644 index 0000000..f46623c --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6fa655976da33926b6a3f05593df7bff15654fee13f43756b80cc709a7ed94 +size 551378080 diff --git a/DeepPrep-Qwen3-0.6B.Q5_K_S.gguf b/DeepPrep-Qwen3-0.6B.Q5_K_S.gguf new file mode 100644 index 0000000..78ca874 --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31477e78d0af95733c064cffe284d59976552808f5a84f216621bfb9512021e0 +size 543579296 diff --git a/DeepPrep-Qwen3-0.6B.Q6_K.gguf b/DeepPrep-Qwen3-0.6B.Q6_K.gguf new file mode 100644 index 0000000..09ff957 --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d85bf221790214fbd2a84ac896d22658d474bc2dd92d855af283c57f530e7df0 +size 622733472 diff --git a/DeepPrep-Qwen3-0.6B.Q8_0.gguf b/DeepPrep-Qwen3-0.6B.Q8_0.gguf new file mode 100644 index 0000000..e8c066f --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87892f5d5ff983ffc90dc9d4a305ba7d9cada6dd4948ad7e83dcd1538611e61a +size 804753568 diff --git a/DeepPrep-Qwen3-0.6B.f16.gguf b/DeepPrep-Qwen3-0.6B.f16.gguf new file mode 100644 index 0000000..d9c69da --- /dev/null +++ b/DeepPrep-Qwen3-0.6B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417834f5b4c188f1c0017598ec87f88a90d7017924717690f3d1ad5b87f11218 +size 1509347488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..534b9b0 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: DeepPrep/DeepPrep-Qwen3-0.6B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DeepPrep/DeepPrep-Qwen3-0.6B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepPrep-Qwen3-0.6B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-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-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.Q6_K.gguf) | Q6_K | 0.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.Q8_0.gguf) | Q8_0 | 0.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepPrep-Qwen3-0.6B-GGUF/resolve/main/DeepPrep-Qwen3-0.6B.f16.gguf) | f16 | 1.6 | 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. + +