commit cafb1f88e5988cde7a8dbf0fe501ce4a95f8fb0e Author: ModelHub XC Date: Thu May 7 15:42:02 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Xiaolong-Qwen3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1262e2f --- /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 +Xiaolong-Qwen3-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..63176ce --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: nbeerbower/Xiaolong-Qwen3-4B +datasets: +- nbeerbower/GreatFirewall-DPO +- nbeerbower/Schule-DPO +- nbeerbower/Purpura-DPO +- nbeerbower/Arkhaios-DPO +- jondurbin/truthy-dpo-v0.1 +- antiven0m/physical-reasoning-dpo +- flammenai/Date-DPO-NoAsterisks +- flammenai/Prude-Phi3-DPO +- Atsunori/HelpSteer2-DPO +- jondurbin/gutenberg-dpo-v0.1 +- nbeerbower/gutenberg2-dpo +- nbeerbower/gutenberg-moderne-dpo +- GeneralReasoning/GeneralThought-430K +- nvidia/OpenMathReasoning +- nvidia/OpenCodeReasoning +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- orpo +- uncensored +- reasoning +- cot +--- +## About + + + + + + +static quants of https://huggingface.co/nbeerbower/Xiaolong-Qwen3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Xiaolong-Qwen3-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-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/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-4B-GGUF/resolve/main/Xiaolong-Qwen3-4B.f16.gguf) | f16 | 8.2 | 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/Xiaolong-Qwen3-4B.IQ4_XS.gguf b/Xiaolong-Qwen3-4B.IQ4_XS.gguf new file mode 100644 index 0000000..e3d9ea6 --- /dev/null +++ b/Xiaolong-Qwen3-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b68040f364b62062e26a4e2e2311b0525550c271e0126845ab1b10e31b56d5f1 +size 2286319968 diff --git a/Xiaolong-Qwen3-4B.Q2_K.gguf b/Xiaolong-Qwen3-4B.Q2_K.gguf new file mode 100644 index 0000000..6435d4e --- /dev/null +++ b/Xiaolong-Qwen3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa6fd87fdf5a7b60b742990788d94924960c97394fe19a9548ce1367e671b5a1 +size 1669503328 diff --git a/Xiaolong-Qwen3-4B.Q3_K_L.gguf b/Xiaolong-Qwen3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..cdd36e0 --- /dev/null +++ b/Xiaolong-Qwen3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de4ca09abc7b5b8ab6bf49baafb7fcdafb24318943dc5ecba83904dbaa53a115 +size 2239789408 diff --git a/Xiaolong-Qwen3-4B.Q3_K_M.gguf b/Xiaolong-Qwen3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..8dc2fa3 --- /dev/null +++ b/Xiaolong-Qwen3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0293ed0f4c31e808331c8bf43e360ab5335e5825b779fb37b256c362ebc2d3a +size 2075621728 diff --git a/Xiaolong-Qwen3-4B.Q3_K_S.gguf b/Xiaolong-Qwen3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..2ad5885 --- /dev/null +++ b/Xiaolong-Qwen3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2bf52fd8fe7665e18a9cef103c3f48cf0dd736fc25c81a0690984bf6a9c339 +size 1887000928 diff --git a/Xiaolong-Qwen3-4B.Q4_K_M.gguf b/Xiaolong-Qwen3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..0b35907 --- /dev/null +++ b/Xiaolong-Qwen3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9973fbe98f49be890e54d7a6567f21dfd99ee32ea196bb1e6575c0bb560409fd +size 2497284448 diff --git a/Xiaolong-Qwen3-4B.Q4_K_S.gguf b/Xiaolong-Qwen3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..fbf80bd --- /dev/null +++ b/Xiaolong-Qwen3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aff0bff044bf2eaebf96b90fcabe0b28b183f1d0fc3b794c577516597904b697 +size 2383313248 diff --git a/Xiaolong-Qwen3-4B.Q5_K_M.gguf b/Xiaolong-Qwen3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..9404a8f --- /dev/null +++ b/Xiaolong-Qwen3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3662b80abe32b858bf9a1fb4123fcb16b14051127a5f1df624bb9ea90e8eae13 +size 2889517408 diff --git a/Xiaolong-Qwen3-4B.Q5_K_S.gguf b/Xiaolong-Qwen3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..e9830a8 --- /dev/null +++ b/Xiaolong-Qwen3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ad14c3668394d7315cb2bead60060a5846053df3b2c2bf093a933cc828a693 +size 2823715168 diff --git a/Xiaolong-Qwen3-4B.Q6_K.gguf b/Xiaolong-Qwen3-4B.Q6_K.gguf new file mode 100644 index 0000000..2bc2d9f --- /dev/null +++ b/Xiaolong-Qwen3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d821c48d095315368b56529bf6a97d962168d8b1c27868e1447a70aadeae099 +size 3306264928 diff --git a/Xiaolong-Qwen3-4B.Q8_0.gguf b/Xiaolong-Qwen3-4B.Q8_0.gguf new file mode 100644 index 0000000..e820a00 --- /dev/null +++ b/Xiaolong-Qwen3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b87d16e96e540ef1465a8b0f19bd78e7289f962078eefeb2d0ba3efacd5e55eb +size 4280408928 diff --git a/Xiaolong-Qwen3-4B.f16.gguf b/Xiaolong-Qwen3-4B.f16.gguf new file mode 100644 index 0000000..6205dda --- /dev/null +++ b/Xiaolong-Qwen3-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b5006fc5a3bbb12a676143b257de72854b6edab6431a94710c9a390f350218 +size 8051288928