commit 49c81526684f4736d9f0ee2f6acbe2b3b3398a86 Author: ModelHub XC Date: Fri May 8 14:29:36 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Xiaolong-Qwen3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c9d0b1d --- /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-Qwen3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Xiaolong-Qwen3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..54cf7cc --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: nbeerbower/Xiaolong-Qwen3-8B +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-Qwen3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Xiaolong-Qwen3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-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-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Xiaolong-Qwen3-8B-GGUF/resolve/main/Xiaolong-Qwen3-8B.f16.gguf) | f16 | 16.5 | 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-Qwen3-8B.IQ4_XS.gguf b/Xiaolong-Qwen3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..7412846 --- /dev/null +++ b/Xiaolong-Qwen3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abef2a79588eda2b4e851c4ee4b57e08ea87038bd6992c49fb7c5ce6edcd1678 +size 4593300352 diff --git a/Xiaolong-Qwen3-8B.Q2_K.gguf b/Xiaolong-Qwen3-8B.Q2_K.gguf new file mode 100644 index 0000000..99e8118 --- /dev/null +++ b/Xiaolong-Qwen3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4644ebd897de3e37fd8ede158ea8364c8992ca81a7db07a606e54be3a5dbc950 +size 3281736576 diff --git a/Xiaolong-Qwen3-8B.Q3_K_L.gguf b/Xiaolong-Qwen3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..3139396 --- /dev/null +++ b/Xiaolong-Qwen3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3347fce03c2591827458fd0b83a5b243ef6e6f7dc5ca0cf69dffb7bc14e567 +size 4431397760 diff --git a/Xiaolong-Qwen3-8B.Q3_K_M.gguf b/Xiaolong-Qwen3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..f2e6576 --- /dev/null +++ b/Xiaolong-Qwen3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eca2dcf80cbe5f66fabffe9be9297f1e36f2a18fa85b1e9f5579073f6dbb6182 +size 4124164992 diff --git a/Xiaolong-Qwen3-8B.Q3_K_S.gguf b/Xiaolong-Qwen3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..b274a88 --- /dev/null +++ b/Xiaolong-Qwen3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc4c55355505b964fac373a955eb58f8d3ed7a3cbc7bb512ef1050c3a5ada92 +size 3769615232 diff --git a/Xiaolong-Qwen3-8B.Q4_K_M.gguf b/Xiaolong-Qwen3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..6f00774 --- /dev/null +++ b/Xiaolong-Qwen3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f6b139143db44be92ea9d359d9ee3eb41d6f611d66db10658f684aa2d863b02 +size 5027787648 diff --git a/Xiaolong-Qwen3-8B.Q4_K_S.gguf b/Xiaolong-Qwen3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..31e18bd --- /dev/null +++ b/Xiaolong-Qwen3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa761aeb6c725c0092de78d028dd528b1b727c10991cff04c872301cb0d5c66 +size 4802016128 diff --git a/Xiaolong-Qwen3-8B.Q5_K_M.gguf b/Xiaolong-Qwen3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..ed4ac9f --- /dev/null +++ b/Xiaolong-Qwen3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc16c5d152169acf67733307f45a1502534b8c91a5c79fdedf36db7ab3de26f5 +size 5851116416 diff --git a/Xiaolong-Qwen3-8B.Q5_K_S.gguf b/Xiaolong-Qwen3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..b2f186d --- /dev/null +++ b/Xiaolong-Qwen3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63af0d04c4ab07b07f055dcf449b7500fdbbd9656ece6fdd8bd9cea02f5c874 +size 5720765312 diff --git a/Xiaolong-Qwen3-8B.Q6_K.gguf b/Xiaolong-Qwen3-8B.Q6_K.gguf new file mode 100644 index 0000000..724cf54 --- /dev/null +++ b/Xiaolong-Qwen3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09742efe1d585de98821754517da23b3ade0fc82b8daf24bcd2a8806c8e5c458 +size 6725903232 diff --git a/Xiaolong-Qwen3-8B.Q8_0.gguf b/Xiaolong-Qwen3-8B.Q8_0.gguf new file mode 100644 index 0000000..2fc0bef --- /dev/null +++ b/Xiaolong-Qwen3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf7967bdbfd1dbf9f5b47aa7958fdfa4dec00eb826fee2182697e5155421195e +size 8709522304 diff --git a/Xiaolong-Qwen3-8B.f16.gguf b/Xiaolong-Qwen3-8B.f16.gguf new file mode 100644 index 0000000..66a57c7 --- /dev/null +++ b/Xiaolong-Qwen3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df03655df66ddd1f9464795a47ea49e9005f3614731b8130fcbb619dfaaed83e +size 16388047744