commit 36b9645f7f6f6f7cc6c9dc0e89a0e41d63e3f37e Author: ModelHub XC Date: Sat Jun 13 06:44:15 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/FlexGuard-Qwen3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a1e023c --- /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 +FlexGuard-Qwen3-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FlexGuard-Qwen3-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FlexGuard-Qwen3-4B.IQ4_XS.gguf b/FlexGuard-Qwen3-4B.IQ4_XS.gguf new file mode 100644 index 0000000..6f161ef --- /dev/null +++ b/FlexGuard-Qwen3-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de80f07280ce83d3c030f531790740a8cd0dfd444913bfedbbf6853bd4975a67 +size 2492949856 diff --git a/FlexGuard-Qwen3-4B.Q2_K.gguf b/FlexGuard-Qwen3-4B.Q2_K.gguf new file mode 100644 index 0000000..d525f9f --- /dev/null +++ b/FlexGuard-Qwen3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a749e5ee394c7e9c3e53ce96002170698793d615aac3a572a0651a1d51de76da +size 1797126496 diff --git a/FlexGuard-Qwen3-4B.Q3_K_L.gguf b/FlexGuard-Qwen3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..ce7befa --- /dev/null +++ b/FlexGuard-Qwen3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555a4fc40616b2377409d1bd25d6e4ff9473dce7ca53987a65808928c90c21e3 +size 2406915936 diff --git a/FlexGuard-Qwen3-4B.Q3_K_M.gguf b/FlexGuard-Qwen3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..8a71010 --- /dev/null +++ b/FlexGuard-Qwen3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1516b935f1f6e936e6cb8395a99719ed29be9685f6251a18ce3f45de22dfad +size 2242748256 diff --git a/FlexGuard-Qwen3-4B.Q3_K_S.gguf b/FlexGuard-Qwen3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..e4fae11 --- /dev/null +++ b/FlexGuard-Qwen3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4d9875d914760cce7f1dfa1db1477bee803264367d04072dc161657e3458c03 +size 2054127456 diff --git a/FlexGuard-Qwen3-4B.Q4_K_M.gguf b/FlexGuard-Qwen3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..f9cd282 --- /dev/null +++ b/FlexGuard-Qwen3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3370308bcf0918ed9740b5e9185676ad3bccc38b69434dd77dd1aa583878ae84 +size 2716069216 diff --git a/FlexGuard-Qwen3-4B.Q4_K_S.gguf b/FlexGuard-Qwen3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..379c035 --- /dev/null +++ b/FlexGuard-Qwen3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eebfb90c7553fed0aa1d3c9996c5f7a22711be5809bfd6a71919104063394b6c +size 2602098016 diff --git a/FlexGuard-Qwen3-4B.Q5_K_M.gguf b/FlexGuard-Qwen3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..5eec930 --- /dev/null +++ b/FlexGuard-Qwen3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6326c6dd5f7fa02fc562e93ca1e09386ef56c14aba52fc3eecedcdcc757a1fe +size 3156921696 diff --git a/FlexGuard-Qwen3-4B.Q5_K_S.gguf b/FlexGuard-Qwen3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..37885e3 --- /dev/null +++ b/FlexGuard-Qwen3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71cd40b55084dc5b838217d3bb456d74b899ccf46249d958a319fedcc1184b08 +size 3091119456 diff --git a/FlexGuard-Qwen3-4B.Q6_K.gguf b/FlexGuard-Qwen3-4B.Q6_K.gguf new file mode 100644 index 0000000..f7650cd --- /dev/null +++ b/FlexGuard-Qwen3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b49f5dbc85148ce3b6e1d7c13272f5b0e50f456211b58f9e91bdc7c378f030 +size 3625327456 diff --git a/FlexGuard-Qwen3-4B.Q8_0.gguf b/FlexGuard-Qwen3-4B.Q8_0.gguf new file mode 100644 index 0000000..a7de4bd --- /dev/null +++ b/FlexGuard-Qwen3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4c34e5aec617561b7233ac0291cb71ea86f591a32e2a8b6a4a118bd044a0548 +size 4693671776 diff --git a/FlexGuard-Qwen3-4B.f16.gguf b/FlexGuard-Qwen3-4B.f16.gguf new file mode 100644 index 0000000..6146d70 --- /dev/null +++ b/FlexGuard-Qwen3-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1e41571b1cc5aeda2539ccef11ae5b4eeb766fe0ff11f3536df4890c4d87c0 +size 8829198176 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1e83ee6 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: Tommy-DING/FlexGuard-Qwen3-4B +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- safety +- moderation +- guardrails +- risk-scoring +- strictness-adaptive +- calibration +- vllm +- transformers +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Tommy-DING/FlexGuard-Qwen3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#FlexGuard-Qwen3-4B-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/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FlexGuard-Qwen3-4B-GGUF/resolve/main/FlexGuard-Qwen3-4B.f16.gguf) | f16 | 8.9 | 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. + +