commit 372dd28f95a95b0c0ab361fcd6b07678d2b71d46 Author: ModelHub XC Date: Thu Jun 4 04:08:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MemPrivacy-4B-RL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f84bf7c --- /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 +MemPrivacy-4B-RL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MemPrivacy-4B-RL.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MemPrivacy-4B-RL.IQ4_XS.gguf b/MemPrivacy-4B-RL.IQ4_XS.gguf new file mode 100644 index 0000000..b9293e5 --- /dev/null +++ b/MemPrivacy-4B-RL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbee62825beb83d09238e4a07658da87d320f647e6fe0174aa73b6ed6d2ce87a +size 2492949696 diff --git a/MemPrivacy-4B-RL.Q2_K.gguf b/MemPrivacy-4B-RL.Q2_K.gguf new file mode 100644 index 0000000..a2fb245 --- /dev/null +++ b/MemPrivacy-4B-RL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0d5dd4c4d8748e5ece0ce72a2484989ae8219b9d30b0ab563f79434e4e37dc4 +size 1797126336 diff --git a/MemPrivacy-4B-RL.Q3_K_L.gguf b/MemPrivacy-4B-RL.Q3_K_L.gguf new file mode 100644 index 0000000..e177dab --- /dev/null +++ b/MemPrivacy-4B-RL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67f3b7aabb1381f05a72694f64345d409d252ed5ca050b026699925dc7445856 +size 2406915776 diff --git a/MemPrivacy-4B-RL.Q3_K_M.gguf b/MemPrivacy-4B-RL.Q3_K_M.gguf new file mode 100644 index 0000000..c41faac --- /dev/null +++ b/MemPrivacy-4B-RL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1e4360f494f8ad95853cf59728f0c1b2cc9a9a3d49fd5a993264b73b435042 +size 2242748096 diff --git a/MemPrivacy-4B-RL.Q3_K_S.gguf b/MemPrivacy-4B-RL.Q3_K_S.gguf new file mode 100644 index 0000000..0b6f177 --- /dev/null +++ b/MemPrivacy-4B-RL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7de8ae3b0bf090ce3a8ac7cc3c19dcd7ce4342d999b55c804d2cd78c0d4270d6 +size 2054127296 diff --git a/MemPrivacy-4B-RL.Q4_K_M.gguf b/MemPrivacy-4B-RL.Q4_K_M.gguf new file mode 100644 index 0000000..1de6b23 --- /dev/null +++ b/MemPrivacy-4B-RL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a28707086a46ef84f1ad17354aae6feec778bbee0fda8aea7e1b8281842203 +size 2716069056 diff --git a/MemPrivacy-4B-RL.Q4_K_S.gguf b/MemPrivacy-4B-RL.Q4_K_S.gguf new file mode 100644 index 0000000..27e3d29 --- /dev/null +++ b/MemPrivacy-4B-RL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db6af1df6f3ae0e163e5587ebcf4f57c028145eaea212d7be390202fdf5f120c +size 2602097856 diff --git a/MemPrivacy-4B-RL.Q5_K_M.gguf b/MemPrivacy-4B-RL.Q5_K_M.gguf new file mode 100644 index 0000000..33bb94f --- /dev/null +++ b/MemPrivacy-4B-RL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8675f242d95f43bdddb7c5f308046211f37de8bcbff686860cf7e1e53d8c8a60 +size 3156921536 diff --git a/MemPrivacy-4B-RL.Q5_K_S.gguf b/MemPrivacy-4B-RL.Q5_K_S.gguf new file mode 100644 index 0000000..2487705 --- /dev/null +++ b/MemPrivacy-4B-RL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db5ca30c706f7f1f9f3e20d8363e044efc96fc754c1da340a3ccf3499634bcb2 +size 3091119296 diff --git a/MemPrivacy-4B-RL.Q6_K.gguf b/MemPrivacy-4B-RL.Q6_K.gguf new file mode 100644 index 0000000..7475624 --- /dev/null +++ b/MemPrivacy-4B-RL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7775f9f8caa1be4fd945de935aa1094bb0a65cd59b77800206b119fe38cbf8 +size 3625327296 diff --git a/MemPrivacy-4B-RL.Q8_0.gguf b/MemPrivacy-4B-RL.Q8_0.gguf new file mode 100644 index 0000000..54560fa --- /dev/null +++ b/MemPrivacy-4B-RL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f2e78ec566ad32b4b237fc42ce52b07031f844d702a820bfb5c57738d488b3d +size 4693671616 diff --git a/MemPrivacy-4B-RL.f16.gguf b/MemPrivacy-4B-RL.f16.gguf new file mode 100644 index 0000000..65001be --- /dev/null +++ b/MemPrivacy-4B-RL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2c7e2169f643a98f2250618cc9ccd103a716ded6bb41590ea3f72cd5918399 +size 8829198016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..66f6f57 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +arxiv: 2605.09530 +base_model: IAAR-Shanghai/MemPrivacy-4B-RL +language: +- en +- zh +library_name: transformers +license: cc-by-nc-nd-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- privacy +- privacy-detection +- memory +- personalized-memory +- memory-system +- memory-management +- agent +- agent-memory +- information-security +- information-extraction +- edge-cloud +--- +## About + + + + + + + + + +static quants of https://huggingface.co/IAAR-Shanghai/MemPrivacy-4B-RL + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MemPrivacy-4B-RL-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/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MemPrivacy-4B-RL-GGUF/resolve/main/MemPrivacy-4B-RL.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. + +