commit 898808ae637f8971486bde2ae0fe28a6a1c3f050 Author: ModelHub XC Date: Tue Jul 21 02:17:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7a40c85 --- /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-RP-Thinker-V2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RP-Thinker-V2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-RP-Thinker-V2.IQ4_XS.gguf b/Qwen2.5-3B-RP-Thinker-V2.IQ4_XS.gguf new file mode 100644 index 0000000..a6d4065 --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2795446119b464a455722c9418592f7db5440ee5b9facbffb40a604f3a123141 +size 1918492352 diff --git a/Qwen2.5-3B-RP-Thinker-V2.Q2_K.gguf b/Qwen2.5-3B-RP-Thinker-V2.Q2_K.gguf new file mode 100644 index 0000000..0375d08 --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17abb32ad94c099b246a26e4c63fd9151789e4d297c9e54b635393512bf0a872 +size 1376857792 diff --git a/Qwen2.5-3B-RP-Thinker-V2.Q3_K_L.gguf b/Qwen2.5-3B-RP-Thinker-V2.Q3_K_L.gguf new file mode 100644 index 0000000..5d9fab3 --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e8702a07c657d3e53449a36f20ddacca0ac84663b9ddf4ad38d81990b75a7c3 +size 1841096384 diff --git a/Qwen2.5-3B-RP-Thinker-V2.Q3_K_M.gguf b/Qwen2.5-3B-RP-Thinker-V2.Q3_K_M.gguf new file mode 100644 index 0000000..5ff5b6b --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f40780641c3673ee4467bd1eb01950efbfe1d549f5a3e2fb0b475a7340f4b596 +size 1724180160 diff --git a/Qwen2.5-3B-RP-Thinker-V2.Q3_K_S.gguf b/Qwen2.5-3B-RP-Thinker-V2.Q3_K_S.gguf new file mode 100644 index 0000000..2cd9c85 --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8875c13647dd4494ef2ed231945dc4c3ea55ea8cf7b11225e62c1c888b8cf9e +size 1588061888 diff --git a/Qwen2.5-3B-RP-Thinker-V2.Q4_K_M.gguf b/Qwen2.5-3B-RP-Thinker-V2.Q4_K_M.gguf new file mode 100644 index 0000000..8dc66b6 --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a017f2c6f9a6f19c138fbbdc626e85dfd4629604d1111f5ada00b3cc97362db8 +size 2104934080 diff --git a/Qwen2.5-3B-RP-Thinker-V2.Q4_K_S.gguf b/Qwen2.5-3B-RP-Thinker-V2.Q4_K_S.gguf new file mode 100644 index 0000000..b72a796 --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95355c54a9a32af9274c8aae6481e1d8e05976a7607c1d7ac2db6a3c4d6abf2b +size 2009415360 diff --git a/Qwen2.5-3B-RP-Thinker-V2.Q5_K_M.gguf b/Qwen2.5-3B-RP-Thinker-V2.Q5_K_M.gguf new file mode 100644 index 0000000..b86142f --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85b0cd7392e04549eccaa072c972f7d1005e2d0c7ffd3483d2bf5614c74fb85 +size 2438741696 diff --git a/Qwen2.5-3B-RP-Thinker-V2.Q5_K_S.gguf b/Qwen2.5-3B-RP-Thinker-V2.Q5_K_S.gguf new file mode 100644 index 0000000..ca36f86 --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac4da803c154896c498486833cb442e957ef6dbc182b25dd014737453d88239 +size 2383593152 diff --git a/Qwen2.5-3B-RP-Thinker-V2.Q6_K.gguf b/Qwen2.5-3B-RP-Thinker-V2.Q6_K.gguf new file mode 100644 index 0000000..743bf4c --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec0aa2e0e870943fdabf650c099f1faa38e4cee493499411953ba3d65bd4d900 +size 2793412288 diff --git a/Qwen2.5-3B-RP-Thinker-V2.Q8_0.gguf b/Qwen2.5-3B-RP-Thinker-V2.Q8_0.gguf new file mode 100644 index 0000000..24cd56b --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51fb4508c6638b19535df691bdd598de4ff68b25845e4fef32163cc8ec92ac30 +size 3616089792 diff --git a/Qwen2.5-3B-RP-Thinker-V2.f16.gguf b/Qwen2.5-3B-RP-Thinker-V2.f16.gguf new file mode 100644 index 0000000..fa68657 --- /dev/null +++ b/Qwen2.5-3B-RP-Thinker-V2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96ce636d79e8d760840ea084370ec8d729288ed7216e5bcaef4e7936677ff2a5 +size 6800647872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..11a8da6 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Qwen2.5-3B-RP-Thinker-V2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen2.5-3B-RP-Thinker-V2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-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/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RP-Thinker-V2-GGUF/resolve/main/Qwen2.5-3B-RP-Thinker-V2.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. + +