commit 0aacf0c153e91d3fc6e729fb108fe479b28bd08e Author: ModelHub XC Date: Sun Apr 26 10:14:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen25-3b-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..33be501 --- /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 +qwen25-3b-abliterated.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen25-3b-abliterated.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d46874b --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: bedderautomation/qwen25-3b-abliterated +datasets: +- bedderautomation/refusal-geometry-qwen25-3b +language: +- en +library_name: transformers +license: apache-2.0 +model_type: qwen2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- abliteration +- uncensored +- qwen2 +- mechanistic-interpretability +- refusal-geometry +--- +## About + + + + + + + + + +static quants of https://huggingface.co/bedderautomation/qwen25-3b-abliterated + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen25-3b-abliterated-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/qwen25-3b-abliterated-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/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen25-3b-abliterated-GGUF/resolve/main/qwen25-3b-abliterated.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. + + diff --git a/qwen25-3b-abliterated.IQ4_XS.gguf b/qwen25-3b-abliterated.IQ4_XS.gguf new file mode 100644 index 0000000..963219a --- /dev/null +++ b/qwen25-3b-abliterated.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7ac31d59fd145ecb9d8a6b22a13203adc0991c7a54ac905bf88911e5a9331a4 +size 1753185920 diff --git a/qwen25-3b-abliterated.Q2_K.gguf b/qwen25-3b-abliterated.Q2_K.gguf new file mode 100644 index 0000000..d3199ad --- /dev/null +++ b/qwen25-3b-abliterated.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb9080eaece2b1e195f6b32adc7888665144030e20af7b598cc8f0dc1dce55f8 +size 1274756736 diff --git a/qwen25-3b-abliterated.Q3_K_L.gguf b/qwen25-3b-abliterated.Q3_K_L.gguf new file mode 100644 index 0000000..f558017 --- /dev/null +++ b/qwen25-3b-abliterated.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff0f6963ff59b16302734c6aeb614622eb41d0155def73cd7add9d07d87b8697 +size 1707392640 diff --git a/qwen25-3b-abliterated.Q3_K_M.gguf b/qwen25-3b-abliterated.Q3_K_M.gguf new file mode 100644 index 0000000..c933153 --- /dev/null +++ b/qwen25-3b-abliterated.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c8c066a89e813ad6b03ea83afefef6c0bad20b93fb5178537d384388c9a5e64 +size 1590476416 diff --git a/qwen25-3b-abliterated.Q3_K_S.gguf b/qwen25-3b-abliterated.Q3_K_S.gguf new file mode 100644 index 0000000..35a40bd --- /dev/null +++ b/qwen25-3b-abliterated.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebba154b2db9051b9d51f4c7c15a51841b14da3ce589640730cc058e904dca31 +size 1454358144 diff --git a/qwen25-3b-abliterated.Q4_K_M.gguf b/qwen25-3b-abliterated.Q4_K_M.gguf new file mode 100644 index 0000000..45cbb55 --- /dev/null +++ b/qwen25-3b-abliterated.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:066f32e4a2b50e29ad7df7c94a1d7bce2f97717921e5ef357fa6c8982044499f +size 1929903744 diff --git a/qwen25-3b-abliterated.Q4_K_S.gguf b/qwen25-3b-abliterated.Q4_K_S.gguf new file mode 100644 index 0000000..ae3b0c8 --- /dev/null +++ b/qwen25-3b-abliterated.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92143a7a3596af245037a1d18fb25596eb915541959bfb7a297197c08f555df1 +size 1834385024 diff --git a/qwen25-3b-abliterated.Q5_K_M.gguf b/qwen25-3b-abliterated.Q5_K_M.gguf new file mode 100644 index 0000000..f0f9810 --- /dev/null +++ b/qwen25-3b-abliterated.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d759eab631caed5af5a5b92c1308267cda8f8b630b9b10b1f020be77712d4a02 +size 2224815744 diff --git a/qwen25-3b-abliterated.Q5_K_S.gguf b/qwen25-3b-abliterated.Q5_K_S.gguf new file mode 100644 index 0000000..b3944b7 --- /dev/null +++ b/qwen25-3b-abliterated.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72133d4220b92eb90e07e027cd2aba1252bd14398df9656918f35410f0aa52c +size 2169667200 diff --git a/qwen25-3b-abliterated.Q6_K.gguf b/qwen25-3b-abliterated.Q6_K.gguf new file mode 100644 index 0000000..ef4d00f --- /dev/null +++ b/qwen25-3b-abliterated.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52cfae46d3c6a18f48e0b72a4d8fed62164ba8fa2354311e5f624b9f5a8d0676 +size 2538159744 diff --git a/qwen25-3b-abliterated.Q8_0.gguf b/qwen25-3b-abliterated.Q8_0.gguf new file mode 100644 index 0000000..05d82b7 --- /dev/null +++ b/qwen25-3b-abliterated.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26abc0d028e1d1d267b69d4210d0a600d569fce034601c681ea30d7eff6b1ea9 +size 3285476992 diff --git a/qwen25-3b-abliterated.f16.gguf b/qwen25-3b-abliterated.f16.gguf new file mode 100644 index 0000000..08d95a7 --- /dev/null +++ b/qwen25-3b-abliterated.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016b3de9bdcd199ed7c691a195b5766d498e1103bb45fcb4163f4887587a1142 +size 6178317952