commit 7abd9c908df8baac89af5da22ca49df74d703990 Author: ModelHub XC Date: Thu Jun 18 06:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-3B-privacy-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2bfb53e --- /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 +llama-3.2-3B-privacy.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-privacy.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0cae9b0 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: EliotShen/llama-3.2-3B-privacy +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- language +--- +## About + + + + + + + + + +static quants of https://huggingface.co/EliotShen/llama-3.2-3B-privacy + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.2-3B-privacy-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/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-privacy-GGUF/resolve/main/llama-3.2-3B-privacy.f16.gguf) | f16 | 6.5 | 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/llama-3.2-3B-privacy.IQ4_XS.gguf b/llama-3.2-3B-privacy.IQ4_XS.gguf new file mode 100644 index 0000000..ce6b2bd --- /dev/null +++ b/llama-3.2-3B-privacy.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90442e6ad26c48d5284c5cf04f8ae2e8ab1a452cbcd3642f87e2186018bf181a +size 1840906880 diff --git a/llama-3.2-3B-privacy.Q2_K.gguf b/llama-3.2-3B-privacy.Q2_K.gguf new file mode 100644 index 0000000..d4b3465 --- /dev/null +++ b/llama-3.2-3B-privacy.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dedd8a49edb8d5a2ea501c50056795eb1237d7b203ddb9e85ebaabb351842318 +size 1363935872 diff --git a/llama-3.2-3B-privacy.Q3_K_L.gguf b/llama-3.2-3B-privacy.Q3_K_L.gguf new file mode 100644 index 0000000..62c9bb5 --- /dev/null +++ b/llama-3.2-3B-privacy.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c0746648adc4b03e7126a714df56f5848d870471386f15f526ea6d0fea4b772 +size 1815347840 diff --git a/llama-3.2-3B-privacy.Q3_K_M.gguf b/llama-3.2-3B-privacy.Q3_K_M.gguf new file mode 100644 index 0000000..9c9d5c5 --- /dev/null +++ b/llama-3.2-3B-privacy.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8754266a5cb15770f701d94bc5dce4df6571291aec9e415c5c3cfe3916062cb8 +size 1687159424 diff --git a/llama-3.2-3B-privacy.Q3_K_S.gguf b/llama-3.2-3B-privacy.Q3_K_S.gguf new file mode 100644 index 0000000..4b9ecd1 --- /dev/null +++ b/llama-3.2-3B-privacy.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac6f60323c5398e292fdfeaaa39be4559d6e4407fea63075a07f6fd098946b6 +size 1542849152 diff --git a/llama-3.2-3B-privacy.Q4_K_M.gguf b/llama-3.2-3B-privacy.Q4_K_M.gguf new file mode 100644 index 0000000..16d06c3 --- /dev/null +++ b/llama-3.2-3B-privacy.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea07967db225921426b8a36ceab52a4bbe49ac4bc56a38220d5062449993c0d6 +size 2019377792 diff --git a/llama-3.2-3B-privacy.Q4_K_S.gguf b/llama-3.2-3B-privacy.Q4_K_S.gguf new file mode 100644 index 0000000..52a0fc8 --- /dev/null +++ b/llama-3.2-3B-privacy.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a0df2ae757e6c5353e2715b8dee92545bc81a96abb048409322c3dcc29a7cf8 +size 1928200832 diff --git a/llama-3.2-3B-privacy.Q5_K_M.gguf b/llama-3.2-3B-privacy.Q5_K_M.gguf new file mode 100644 index 0000000..37351eb --- /dev/null +++ b/llama-3.2-3B-privacy.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0adeeef032af0ebeda6d100b4288f32c36b474e2937bfdfa700b3b4ca940479 +size 2322154112 diff --git a/llama-3.2-3B-privacy.Q5_K_S.gguf b/llama-3.2-3B-privacy.Q5_K_S.gguf new file mode 100644 index 0000000..74c7001 --- /dev/null +++ b/llama-3.2-3B-privacy.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8ffbab0067e7baf6ecbeda963881868be3700a379f723a02e0f776a8f72b596 +size 2269512320 diff --git a/llama-3.2-3B-privacy.Q6_K.gguf b/llama-3.2-3B-privacy.Q6_K.gguf new file mode 100644 index 0000000..e099495 --- /dev/null +++ b/llama-3.2-3B-privacy.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd6da899a9d36f1c6fdcf2dad3bb6623f630581c2e982955c149d6cd8a79a006 +size 2643853952 diff --git a/llama-3.2-3B-privacy.Q8_0.gguf b/llama-3.2-3B-privacy.Q8_0.gguf new file mode 100644 index 0000000..19621ef --- /dev/null +++ b/llama-3.2-3B-privacy.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:265f31f659d70677965897c280807348e31acbd1d031f7bf5cfcc34d34531ece +size 3421899392 diff --git a/llama-3.2-3B-privacy.f16.gguf b/llama-3.2-3B-privacy.f16.gguf new file mode 100644 index 0000000..c7f6a9d --- /dev/null +++ b/llama-3.2-3B-privacy.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32f30922e34f1d5a453bec46c37a9189c8686784527b3ea00db0d12f3402f095 +size 6433688192