commit 872ce230fb3163cda9b6fbeb6360cc37210d5f21 Author: ModelHub XC Date: Sat Apr 11 17:58:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e4f8575 --- /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 +Qwen3-0.6B-Math-Expert-abliterated.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Math-Expert-abliterated.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Math-Expert-abliterated.IQ4_XS.gguf b/Qwen3-0.6B-Math-Expert-abliterated.IQ4_XS.gguf new file mode 100644 index 0000000..918de5a --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0612812c9c84f98ae9a7093cf31dcc53543102239fa6923ed9a3093c49ffb65 +size 369279552 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.Q2_K.gguf b/Qwen3-0.6B-Math-Expert-abliterated.Q2_K.gguf new file mode 100644 index 0000000..7ea7084 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e68813019123380f2fe3c3af562562b78bc53eb025268c3c238161b533fa18 +size 296239680 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_L.gguf b/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_L.gguf new file mode 100644 index 0000000..ac7c4d2 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f19bac0f45f5d9c26b969124cc802719565e596cae4723593566b59cbf80476 +size 368493120 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_M.gguf b/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_M.gguf new file mode 100644 index 0000000..26d26b0 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f621e1893cc8f07940125e1738c9f481c7e89c795db2b5c2ce5e768998fc8bce +size 347128384 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_S.gguf b/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_S.gguf new file mode 100644 index 0000000..f637509 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c326cfc5170d375644aeb9b347ba89cd7e49b0b819bfb3a1e52ed22d2f8768f +size 323076672 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.Q4_K_M.gguf b/Qwen3-0.6B-Math-Expert-abliterated.Q4_K_M.gguf new file mode 100644 index 0000000..a37b60d --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:391cb27af50e220d7b6283dc514e71b0e40e74fceadcf46f461a8f327bd2cfba +size 396706368 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.Q4_K_S.gguf b/Qwen3-0.6B-Math-Expert-abliterated.Q4_K_S.gguf new file mode 100644 index 0000000..661713a --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9ea935d0128ffadc0ad266ac377dc22884e0d6606dc9742d0ae5caec2c2f04 +size 383271488 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.Q5_K_M.gguf b/Qwen3-0.6B-Math-Expert-abliterated.Q5_K_M.gguf new file mode 100644 index 0000000..3fdea13 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a413ccc811274b89b7aa229327ea4a02dc79f2e059630710ffff5d3dd02f0156 +size 444416576 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.Q5_K_S.gguf b/Qwen3-0.6B-Math-Expert-abliterated.Q5_K_S.gguf new file mode 100644 index 0000000..12f113b --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:331ef8642575054d7d86f14b3372562a7b42b4b4434e6d2cd6a4a5bb861293c8 +size 436617792 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.Q6_K.gguf b/Qwen3-0.6B-Math-Expert-abliterated.Q6_K.gguf new file mode 100644 index 0000000..02d8c4f --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cff64a5a6f6dd61e97818416b97e66f189de9fd01c33a7360732bca72b1b24b +size 495108672 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.Q8_0.gguf b/Qwen3-0.6B-Math-Expert-abliterated.Q8_0.gguf new file mode 100644 index 0000000..edac6fd --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:676feb45a039e3ae540f3edbf660a5aed9c5ee76d2204d2a23440e228290e056 +size 639448640 diff --git a/Qwen3-0.6B-Math-Expert-abliterated.f16.gguf b/Qwen3-0.6B-Math-Expert-abliterated.f16.gguf new file mode 100644 index 0000000..02ea9a0 --- /dev/null +++ b/Qwen3-0.6B-Math-Expert-abliterated.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1820e320b35a39326fd4be920c6d4c1e41e6efa50fcab915e81524b1e4516b43 +size 1198184000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0a2ffb9 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: lunahr/Qwen3-0.6B-Math-Expert-abliterated +datasets: +- unsloth/OpenMathReasoning-mini +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +- math +- reasoning +- abliterated +- baukit-abliterated +--- +## About + + + + + + +static quants of https://huggingface.co/lunahr/Qwen3-0.6B-Math-Expert-abliterated + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Math-Expert-abliterated-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/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Math-Expert-abliterated-GGUF/resolve/main/Qwen3-0.6B-Math-Expert-abliterated.f16.gguf) | f16 | 1.3 | 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. + +