commit ad9be540b0080ec7334784fa178fe6d62722ced2 Author: ModelHub XC Date: Wed Jul 8 06:10:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f43a0b4 --- /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 +RealGuardrails-Llama3.2-3B-Instruct-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RealGuardrails-Llama3.2-3B-Instruct-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2d95b57 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: normster/RealGuardrails-Llama3.2-3B-Instruct-SFT +datasets: +- normster/RealGuardrails +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/normster/RealGuardrails-Llama3.2-3B-Instruct-SFT + + +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/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RealGuardrails-Llama3.2-3B-Instruct-SFT-GGUF/resolve/main/RealGuardrails-Llama3.2-3B-Instruct-SFT.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/RealGuardrails-Llama3.2-3B-Instruct-SFT.IQ4_XS.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..7754ea4 --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ddcdab9d588de80c848c9e5690b88467ca5edf8c02658ab053b484b43c4c196 +size 1840904576 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q2_K.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q2_K.gguf new file mode 100644 index 0000000..f54ba78 --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22bbd7d88854f21af1718a9595f17c9d798a0a937e0b6d78bb3d2d2aa82046e5 +size 1363933568 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_L.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..ab6f0a5 --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd013c9f2baa58b09b2d4a2b7b6c152737758ad4f26f22b4e046e4a898223d3b +size 1815345536 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_M.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..a96fad2 --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9020fcb7620fc3939920332390306239984cb48eb045805d76045653ecc94ab2 +size 1687157120 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_S.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..5fe78b2 --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f780835cffbb31e64c938f50e29ca594170b0b0a7a4558455f3b1414df1d92 +size 1542846848 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q4_K_M.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..f74e80e --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da67bd9a002404b74ae7d427ed7cb7ab5fcac490b190facc8b6d2b9852bf3d2e +size 2019375488 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q4_K_S.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..30a045d --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84bf49ae4a71a6d80185b55bd779afa7b2e585288bd03bb435ecc2b9ef89f87c +size 1928198528 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q5_K_M.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..8b04f76 --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efa7032982945bc994e1c6947a49cfeb1826dc8c3607a630a6426e3c63ad9fa8 +size 2322151808 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q5_K_S.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..abf394c --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e78bb40a91fc90ab58202e9f6d558dd8880c9b3b7b1face35fd8bdcfd5dedc +size 2269510016 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q6_K.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q6_K.gguf new file mode 100644 index 0000000..705133a --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b8382c19483631ae70de00aae3b7d4119513ec18cdd0c7bb29d0c5d64d29912 +size 2643851648 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q8_0.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q8_0.gguf new file mode 100644 index 0000000..b96119d --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e7d5b0c658052d80c098b8b83932a3abaa3bc64f961f17dab9624555ba4155 +size 3421897088 diff --git a/RealGuardrails-Llama3.2-3B-Instruct-SFT.f16.gguf b/RealGuardrails-Llama3.2-3B-Instruct-SFT.f16.gguf new file mode 100644 index 0000000..a381693 --- /dev/null +++ b/RealGuardrails-Llama3.2-3B-Instruct-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90cf05cf1546336acf2b1c8beabcdbd26a0b2eb12b934777b300012d777a5d35 +size 6433685888