commit 88f0c2ca40ecc51fc7268c80f19708c7e2e80966 Author: ModelHub XC Date: Fri Apr 24 13:08:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen2.5-1.5B_rewriter-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5742bbf --- /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 +qwen2.5-1.5B_rewriter.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-1.5B_rewriter.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..dca2f0d --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: hirmnm/qwen2.5-1.5B_rewriter +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qwen2.5 +- query-rewriting +- router +- qlora +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hirmnm/qwen2.5-1.5B_rewriter + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen2.5-1.5B_rewriter-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-1.5B_rewriter-GGUF/resolve/main/qwen2.5-1.5B_rewriter.f16.gguf) | f16 | 3.2 | 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. + + diff --git a/qwen2.5-1.5B_rewriter.IQ4_XS.gguf b/qwen2.5-1.5B_rewriter.IQ4_XS.gguf new file mode 100644 index 0000000..b1ababc --- /dev/null +++ b/qwen2.5-1.5B_rewriter.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f5bcddfaec123de4a2a17993979aac8697f7dbcb1c4bd3bac8ed024e1d70d3 +size 902183392 diff --git a/qwen2.5-1.5B_rewriter.Q2_K.gguf b/qwen2.5-1.5B_rewriter.Q2_K.gguf new file mode 100644 index 0000000..5810ddd --- /dev/null +++ b/qwen2.5-1.5B_rewriter.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62fc67e20d71e5ea0b276567c84206f923f47345244338cfb097b57cd9ab5984 +size 676305376 diff --git a/qwen2.5-1.5B_rewriter.Q3_K_L.gguf b/qwen2.5-1.5B_rewriter.Q3_K_L.gguf new file mode 100644 index 0000000..fa4c3fd --- /dev/null +++ b/qwen2.5-1.5B_rewriter.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba39569b9f1cbdc59d15a55a6fb929f7e1ec329c4834cb20bc732ad8cb3b81b +size 880163296 diff --git a/qwen2.5-1.5B_rewriter.Q3_K_M.gguf b/qwen2.5-1.5B_rewriter.Q3_K_M.gguf new file mode 100644 index 0000000..ff02fc6 --- /dev/null +++ b/qwen2.5-1.5B_rewriter.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e25c1633866a980bf3c43e41d50636b727794e2303c42f236dd632bb3fc70da1 +size 824179168 diff --git a/qwen2.5-1.5B_rewriter.Q3_K_S.gguf b/qwen2.5-1.5B_rewriter.Q3_K_S.gguf new file mode 100644 index 0000000..6736c86 --- /dev/null +++ b/qwen2.5-1.5B_rewriter.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:395fdd08b4b372d801abc0bdabce1e3ea6737ea997dfd64c6fce3627a10a89a0 +size 760945120 diff --git a/qwen2.5-1.5B_rewriter.Q4_K_M.gguf b/qwen2.5-1.5B_rewriter.Q4_K_M.gguf new file mode 100644 index 0000000..d6686ba --- /dev/null +++ b/qwen2.5-1.5B_rewriter.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef48bb847f67b5f7bdc02ae0aa6f3867baf7d8dc012cb52fa9c8d79ff628fde0 +size 986048992 diff --git a/qwen2.5-1.5B_rewriter.Q4_K_S.gguf b/qwen2.5-1.5B_rewriter.Q4_K_S.gguf new file mode 100644 index 0000000..6d0877f --- /dev/null +++ b/qwen2.5-1.5B_rewriter.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9652b517b9b3bb235e2bbff18955aee53435322f093b4e8dc15b521761154c +size 940313056 diff --git a/qwen2.5-1.5B_rewriter.Q5_K_M.gguf b/qwen2.5-1.5B_rewriter.Q5_K_M.gguf new file mode 100644 index 0000000..0705f04 --- /dev/null +++ b/qwen2.5-1.5B_rewriter.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944ae2b86aa4135be54304b98cb0280699b8c40c2cd09a5a8ef8f3e1ebfcd8be +size 1125050848 diff --git a/qwen2.5-1.5B_rewriter.Q5_K_S.gguf b/qwen2.5-1.5B_rewriter.Q5_K_S.gguf new file mode 100644 index 0000000..4a6427b --- /dev/null +++ b/qwen2.5-1.5B_rewriter.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27ddeadea2847d7b85d0b1ee5cef3fc236225305a25e882994318ab46447eb6e +size 1098729952 diff --git a/qwen2.5-1.5B_rewriter.Q6_K.gguf b/qwen2.5-1.5B_rewriter.Q6_K.gguf new file mode 100644 index 0000000..a4deb9e --- /dev/null +++ b/qwen2.5-1.5B_rewriter.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aed6ae66dc69ab6832e7f5ebece89f3cb901ef715cec0c6bbe2fe7b70142890a +size 1272740320 diff --git a/qwen2.5-1.5B_rewriter.Q8_0.gguf b/qwen2.5-1.5B_rewriter.Q8_0.gguf new file mode 100644 index 0000000..e1f974c --- /dev/null +++ b/qwen2.5-1.5B_rewriter.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b1f1fa8f53241c0376d3c779c5a7b75a7175a7f804d155f4d26f22a71944dc +size 1646573536 diff --git a/qwen2.5-1.5B_rewriter.f16.gguf b/qwen2.5-1.5B_rewriter.f16.gguf new file mode 100644 index 0000000..3c4c1bf --- /dev/null +++ b/qwen2.5-1.5B_rewriter.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c70f8ec63309d4a3f8a1b3cdaf6aed93329758b386c7f7db21753e809650b4d +size 3093669856