commit 34cb77bcf315cf061711bc91c6ebfeeb1a091dd7 Author: ModelHub XC Date: Mon May 25 02:27:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-rat-polished-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ab79555 --- /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 +Qwen2.5-3B-rat-polished.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-rat-polished.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-rat-polished.IQ4_XS.gguf b/Qwen2.5-3B-rat-polished.IQ4_XS.gguf new file mode 100644 index 0000000..cdbdf34 --- /dev/null +++ b/Qwen2.5-3B-rat-polished.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:817fdbabc75842d212f7fe53a4a1c87dc224ac9d9327b0ae474314005a419aff +size 1753185088 diff --git a/Qwen2.5-3B-rat-polished.Q2_K.gguf b/Qwen2.5-3B-rat-polished.Q2_K.gguf new file mode 100644 index 0000000..5c5e22b --- /dev/null +++ b/Qwen2.5-3B-rat-polished.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bedb01e4f1582134693bb87a0f9fed815433142b641550340d061f3e09d093d6 +size 1274755904 diff --git a/Qwen2.5-3B-rat-polished.Q3_K_L.gguf b/Qwen2.5-3B-rat-polished.Q3_K_L.gguf new file mode 100644 index 0000000..19f1739 --- /dev/null +++ b/Qwen2.5-3B-rat-polished.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c76bbebc7b468d639838fcd0456f8d5727c3c79caaacf2dd331467caaaeaf667 +size 1707391808 diff --git a/Qwen2.5-3B-rat-polished.Q3_K_M.gguf b/Qwen2.5-3B-rat-polished.Q3_K_M.gguf new file mode 100644 index 0000000..5c70176 --- /dev/null +++ b/Qwen2.5-3B-rat-polished.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2378a3f800a046b4250700a8abfa82777a9ae3225ff203a872c2e06166ff29a +size 1590475584 diff --git a/Qwen2.5-3B-rat-polished.Q3_K_S.gguf b/Qwen2.5-3B-rat-polished.Q3_K_S.gguf new file mode 100644 index 0000000..f524c63 --- /dev/null +++ b/Qwen2.5-3B-rat-polished.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64be681a91f8d785e811d058a5d27fcb78761a9b945f64278e4c642aeaa50aa4 +size 1454357312 diff --git a/Qwen2.5-3B-rat-polished.Q4_K_M.gguf b/Qwen2.5-3B-rat-polished.Q4_K_M.gguf new file mode 100644 index 0000000..f7fe410 --- /dev/null +++ b/Qwen2.5-3B-rat-polished.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3571a9e99107bec39cfde59879381053ddfc107bf8b5b973e147ed5ebfbaba27 +size 1929902912 diff --git a/Qwen2.5-3B-rat-polished.Q4_K_S.gguf b/Qwen2.5-3B-rat-polished.Q4_K_S.gguf new file mode 100644 index 0000000..ea02669 --- /dev/null +++ b/Qwen2.5-3B-rat-polished.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc425389bbe5fb76a43c0c0840b4656d76c6a5b76f040cd5094423e1188a5cf0 +size 1834384192 diff --git a/Qwen2.5-3B-rat-polished.Q5_K_M.gguf b/Qwen2.5-3B-rat-polished.Q5_K_M.gguf new file mode 100644 index 0000000..81f618f --- /dev/null +++ b/Qwen2.5-3B-rat-polished.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6291a7583647dbe0c5cead6f612c69bca25cc09481afce567f3b16d987c14b +size 2224814912 diff --git a/Qwen2.5-3B-rat-polished.Q5_K_S.gguf b/Qwen2.5-3B-rat-polished.Q5_K_S.gguf new file mode 100644 index 0000000..58dc728 --- /dev/null +++ b/Qwen2.5-3B-rat-polished.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a1faa42f648088c635b4088c8b526d20a88aa633b3c1922f931813c5f2beb57 +size 2169666368 diff --git a/Qwen2.5-3B-rat-polished.Q6_K.gguf b/Qwen2.5-3B-rat-polished.Q6_K.gguf new file mode 100644 index 0000000..3f30005 --- /dev/null +++ b/Qwen2.5-3B-rat-polished.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e2bd5a81ded699930aec353b34f34a810c3ad76638d6f63e6f0e1b1a1061de +size 2538158912 diff --git a/Qwen2.5-3B-rat-polished.Q8_0.gguf b/Qwen2.5-3B-rat-polished.Q8_0.gguf new file mode 100644 index 0000000..45465cf --- /dev/null +++ b/Qwen2.5-3B-rat-polished.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25754a3c599bcaa90ae08c611b88f2c4280f5a3de83a9fa77a61b4fbb016a68a +size 3285476160 diff --git a/Qwen2.5-3B-rat-polished.f16.gguf b/Qwen2.5-3B-rat-polished.f16.gguf new file mode 100644 index 0000000..6b55249 --- /dev/null +++ b/Qwen2.5-3B-rat-polished.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b69f817bc7be53f7a29a0c1d09ce0385227a717f47c882afcc4962d6aceb3ad4 +size 6178317120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8da79bb --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: Time-Reasoning/Qwen2.5-3B-rat-polished +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Time-Reasoning/Qwen2.5-3B-rat-polished + + +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/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-rat-polished-GGUF/resolve/main/Qwen2.5-3B-rat-polished.f16.gguf) | f16 | 6.3 | 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. + +