commit 56fc295beb384a6a86d9e382101a4500b04d0a3e Author: ModelHub XC Date: Wed May 6 08:00:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/HalluGuard-Qwen3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..80d7c8a --- /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 +HalluGuard-Qwen3-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +HalluGuard-Qwen3-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/HalluGuard-Qwen3-4B.IQ4_XS.gguf b/HalluGuard-Qwen3-4B.IQ4_XS.gguf new file mode 100644 index 0000000..ab5cdd3 --- /dev/null +++ b/HalluGuard-Qwen3-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b878a1e3e3db84411af7b2eeb4a4e422d15b3095bc2a588e83ccb951c7ec4aa +size 2286317600 diff --git a/HalluGuard-Qwen3-4B.Q2_K.gguf b/HalluGuard-Qwen3-4B.Q2_K.gguf new file mode 100644 index 0000000..45b42a1 --- /dev/null +++ b/HalluGuard-Qwen3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae817643d1ac47a37261259004a97c2c3209c4a042b32011d2db0caf0124450 +size 1669500960 diff --git a/HalluGuard-Qwen3-4B.Q3_K_L.gguf b/HalluGuard-Qwen3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..22aa01d --- /dev/null +++ b/HalluGuard-Qwen3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21fca48b0717387093f5403be1728edeb08ed7f91c72839fff023a82ba05ea64 +size 2239787040 diff --git a/HalluGuard-Qwen3-4B.Q3_K_M.gguf b/HalluGuard-Qwen3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..f989b10 --- /dev/null +++ b/HalluGuard-Qwen3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c2cfa8642aa8d245917c1866b0eb3b24d5ba4abbf03bde0f477de2a69be9d2 +size 2075619360 diff --git a/HalluGuard-Qwen3-4B.Q3_K_S.gguf b/HalluGuard-Qwen3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..02ca9da --- /dev/null +++ b/HalluGuard-Qwen3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf678b6ba72be5399857e1e2766f7d04d5516c8aaf1ddac96eb6274ed7fb1b2f +size 1886998560 diff --git a/HalluGuard-Qwen3-4B.Q4_K_M.gguf b/HalluGuard-Qwen3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..61881ff --- /dev/null +++ b/HalluGuard-Qwen3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2346fbf863b2af6feeef5c17625fccfe86cf36941bc0c191fa4c1ee26334423c +size 2497282080 diff --git a/HalluGuard-Qwen3-4B.Q4_K_S.gguf b/HalluGuard-Qwen3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..fd22d57 --- /dev/null +++ b/HalluGuard-Qwen3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fca3d04302efd8490a7d2f087256302889711317278d89ebc6d8d03c72bfacec +size 2383310880 diff --git a/HalluGuard-Qwen3-4B.Q5_K_M.gguf b/HalluGuard-Qwen3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..ed2cd3e --- /dev/null +++ b/HalluGuard-Qwen3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0f685e555239644fb0270487dc5a724968eae1d07ddcbccc1951585e95f312 +size 2889515040 diff --git a/HalluGuard-Qwen3-4B.Q5_K_S.gguf b/HalluGuard-Qwen3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..81cadb5 --- /dev/null +++ b/HalluGuard-Qwen3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bba462c69e83799fd0a420c98348cc142d5ad15ed2bf5e1d6d353a5aefbc718 +size 2823712800 diff --git a/HalluGuard-Qwen3-4B.Q6_K.gguf b/HalluGuard-Qwen3-4B.Q6_K.gguf new file mode 100644 index 0000000..39647fa --- /dev/null +++ b/HalluGuard-Qwen3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e23d79319319a9fdde3cb9fc94c82b50eaba0757988ddb443fedb9d90f06db9 +size 3306262560 diff --git a/HalluGuard-Qwen3-4B.Q8_0.gguf b/HalluGuard-Qwen3-4B.Q8_0.gguf new file mode 100644 index 0000000..a149dc1 --- /dev/null +++ b/HalluGuard-Qwen3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8adb03389a7200d1440d517f08483ca2ea7fc397ee4869bcadb7db2ff199ac4 +size 4280406560 diff --git a/HalluGuard-Qwen3-4B.f16.gguf b/HalluGuard-Qwen3-4B.f16.gguf new file mode 100644 index 0000000..aa2c266 --- /dev/null +++ b/HalluGuard-Qwen3-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3bb430c55dd8e30fcfa82a78d4398b54ef5566215bd142b7416d1631907e38 +size 8051286560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..27b52a5 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: lrsbrgrn/HalluGuard-Qwen3-4B +datasets: +- lrsbrgrn/HalluGuard-Preferences-76k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- hallucination-detection +- retrieval-augmented-generation +- rag +- fact-checking +- small-reasoning-model +--- +## About + + + + + + + + + +static quants of https://huggingface.co/lrsbrgrn/HalluGuard-Qwen3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#HalluGuard-Qwen3-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/HalluGuard-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/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-Qwen3-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/HalluGuard-Qwen3-4B-GGUF/resolve/main/HalluGuard-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. + +