commit 0fbb30635188ba1f67659b527f9e5f9f27028b23 Author: ModelHub XC Date: Sun Sep 6 02:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QwenGuard-v1.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..541258f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +QwenGuard-v1.2-3B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QwenGuard-v1.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QwenGuard-v1.2-3B.IQ4_XS.gguf b/QwenGuard-v1.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..ddb7f15 --- /dev/null +++ b/QwenGuard-v1.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21587be8878146ee67b15580e4bcb224ef2152df2b80b9b95b38410aed82ddae +size 1753185760 diff --git a/QwenGuard-v1.2-3B.Q2_K.gguf b/QwenGuard-v1.2-3B.Q2_K.gguf new file mode 100644 index 0000000..52fe9df --- /dev/null +++ b/QwenGuard-v1.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec498c478947c7ac2c84f4bc4b9b68b0ced6e2b84a897d6d3a09445b7e406dd +size 1274756576 diff --git a/QwenGuard-v1.2-3B.Q3_K_L.gguf b/QwenGuard-v1.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..9ac03a8 --- /dev/null +++ b/QwenGuard-v1.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e48be8f922bcf5b03c08fed0242b82ea6c812a8d3bfe903ca95df7dd93dee98 +size 1707392480 diff --git a/QwenGuard-v1.2-3B.Q3_K_M.gguf b/QwenGuard-v1.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..c02ada3 --- /dev/null +++ b/QwenGuard-v1.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99de6b2a803457aca656afd30ffecbc0bae5509f76b44b3116dc6f20023f1dac +size 1590476256 diff --git a/QwenGuard-v1.2-3B.Q3_K_S.gguf b/QwenGuard-v1.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..f3c0853 --- /dev/null +++ b/QwenGuard-v1.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9560fa8c54809fc8b201f5304a3b85d674411511b81209a66c4f4bc3509273 +size 1454357984 diff --git a/QwenGuard-v1.2-3B.Q4_K_M.gguf b/QwenGuard-v1.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..addd6f7 --- /dev/null +++ b/QwenGuard-v1.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d80433e73e7779e1352413986da04a4323754afadeae0034ae438add495f6532 +size 1929903584 diff --git a/QwenGuard-v1.2-3B.Q4_K_S.gguf b/QwenGuard-v1.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..9493190 --- /dev/null +++ b/QwenGuard-v1.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b50fe4f7a7f6b95c366d5e1aed60a47946e6f62af6ec713446f0af781f0934a +size 1834384864 diff --git a/QwenGuard-v1.2-3B.Q5_K_M.gguf b/QwenGuard-v1.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..6c1bf1a --- /dev/null +++ b/QwenGuard-v1.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:517350b95fac207111523f3fff2dfc96feba8db485ca3b81b30577c26f9de424 +size 2224815584 diff --git a/QwenGuard-v1.2-3B.Q5_K_S.gguf b/QwenGuard-v1.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..2a8ea83 --- /dev/null +++ b/QwenGuard-v1.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf3cd938808647f1af75e1376b490fcd21ddc4cb542b9c85368ecfc4225dbfb +size 2169667040 diff --git a/QwenGuard-v1.2-3B.Q6_K.gguf b/QwenGuard-v1.2-3B.Q6_K.gguf new file mode 100644 index 0000000..be0c1d0 --- /dev/null +++ b/QwenGuard-v1.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de987a024005002465da14de03fdce0c928fe6a51f4ca7a87a8088ef6ce4b1d2 +size 2538159584 diff --git a/QwenGuard-v1.2-3B.Q8_0.gguf b/QwenGuard-v1.2-3B.Q8_0.gguf new file mode 100644 index 0000000..87f4cf7 --- /dev/null +++ b/QwenGuard-v1.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b3e0631ed78246cb0560ab0bea6a8db29b18b115731cc9a298a158c549c6fe +size 3285476832 diff --git a/QwenGuard-v1.2-3B.f16.gguf b/QwenGuard-v1.2-3B.f16.gguf new file mode 100644 index 0000000..f7dde9d --- /dev/null +++ b/QwenGuard-v1.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cf37824a5c0f692c70e7e718bd4d01f6e2485006b967c54b9a68dcde345b0c8 +size 6178317792 diff --git a/QwenGuard-v1.2-3B.mmproj-Q8_0.gguf b/QwenGuard-v1.2-3B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..4cdc5c6 --- /dev/null +++ b/QwenGuard-v1.2-3B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:107df0264f6c4aa58623c7b99339e067baae03207e4424339b10ad17e37c5fda +size 844758400 diff --git a/QwenGuard-v1.2-3B.mmproj-f16.gguf b/QwenGuard-v1.2-3B.mmproj-f16.gguf new file mode 100644 index 0000000..ca8af00 --- /dev/null +++ b/QwenGuard-v1.2-3B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b914ffeb55e277dbe7359ca0d9b05360b3de635bb7678952be57b28412460a +size 1338428800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4588794 --- /dev/null +++ b/README.md @@ -0,0 +1,93 @@ +--- +base_model: AIML-TUDA/QwenGuard-v1.2-3B +datasets: AIML-TUDA/LlavaGuard +extra_gated_fields: + Affiliation: text + Country: text + Email: text + ? I have explicitly checked that downloading LlavaGuard is legal in my jurisdiction, + in the country/region where I am located right now, and for the use case that + I have described above, I have also read and accepted the relevant Terms of Use + : checkbox + Name: text +extra_gated_prompt: By filling out the form below I understand that LlavaGuard is + a derivative model based on webscraped images and the SMID dataset that use individual + licenses and their respective terms and conditions apply. I understand that all + content uses are subject to the terms of use. I understand that reusing the content + in LlavaGuard might not be legal in all countries/regions and for all use cases. + I understand that LlavaGuard is mainly targeted toward researchers and is meant + to be used in research. LlavaGuard authors reserve the right to revoke my access + to this data. They reserve the right to modify this data at any time in accordance + with take-down requests. +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- freeze +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/AIML-TUDA/QwenGuard-v1.2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QwenGuard-v1.2-3B-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/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QwenGuard-v1.2-3B-GGUF/resolve/main/QwenGuard-v1.2-3B.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. + +