commit 37f7d6216445bff756c75394535575f078b18743 Author: ModelHub XC Date: Mon Jun 15 20:52:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d3e2bed --- /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 +Safe-RLHF-SFT-llama3-3b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Safe-RLHF-SFT-llama3-3b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..34acf31 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: Ren-Wei/Safe-RLHF-SFT-llama3-3b +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Ren-Wei/Safe-RLHF-SFT-llama3-3b + + +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/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Safe-RLHF-SFT-llama3-3b-GGUF/resolve/main/Safe-RLHF-SFT-llama3-3b.f16.gguf) | f16 | 7.3 | 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. + + diff --git a/Safe-RLHF-SFT-llama3-3b.IQ4_XS.gguf b/Safe-RLHF-SFT-llama3-3b.IQ4_XS.gguf new file mode 100644 index 0000000..b79a575 --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09457fa1adea8ca18fe4fe6e29e60048062d314b00d187e1b6d6c3355f91789 +size 2050225088 diff --git a/Safe-RLHF-SFT-llama3-3b.Q2_K.gguf b/Safe-RLHF-SFT-llama3-3b.Q2_K.gguf new file mode 100644 index 0000000..44fc33d --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a52857f076bfb4c538afd4c96b1f50d1cfaf4d1513103cdbcb5f380ee92882 +size 1493221088 diff --git a/Safe-RLHF-SFT-llama3-3b.Q3_K_L.gguf b/Safe-RLHF-SFT-llama3-3b.Q3_K_L.gguf new file mode 100644 index 0000000..f9aa47b --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d94b842693de82d914a5b898c004e06d6d1a7a076421ac4bb8d50116214fabb +size 1984649568 diff --git a/Safe-RLHF-SFT-llama3-3b.Q3_K_M.gguf b/Safe-RLHF-SFT-llama3-3b.Q3_K_M.gguf new file mode 100644 index 0000000..5b01f03 --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:203fae0020674f20bee57ac046a664e9a42611a1976492bb3147e4201b40db22 +size 1856461152 diff --git a/Safe-RLHF-SFT-llama3-3b.Q3_K_S.gguf b/Safe-RLHF-SFT-llama3-3b.Q3_K_S.gguf new file mode 100644 index 0000000..edf4c35 --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80d27055f6af77f55c3f791b89c49d9419b2707a3ed53cc1ea1fa56e67693a7 +size 1712150880 diff --git a/Safe-RLHF-SFT-llama3-3b.Q4_K_M.gguf b/Safe-RLHF-SFT-llama3-3b.Q4_K_M.gguf new file mode 100644 index 0000000..f234252 --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b68527d5800681c25e1430b04f1ce49b1d6aac9e88b1bc855b75082a4acf0096 +size 2241008768 diff --git a/Safe-RLHF-SFT-llama3-3b.Q4_K_S.gguf b/Safe-RLHF-SFT-llama3-3b.Q4_K_S.gguf new file mode 100644 index 0000000..47f1228 --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28c41b0622ddaf2dd3899b076b84ae6675c2f136fa785eff3a720c8922b3cade +size 2149831808 diff --git a/Safe-RLHF-SFT-llama3-3b.Q5_K_M.gguf b/Safe-RLHF-SFT-llama3-3b.Q5_K_M.gguf new file mode 100644 index 0000000..298e058 --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc814fe4fbcf43037115b05a7ba4086b018c1212d6e89256e8f3c9115aaa2f5e +size 2593036160 diff --git a/Safe-RLHF-SFT-llama3-3b.Q5_K_S.gguf b/Safe-RLHF-SFT-llama3-3b.Q5_K_S.gguf new file mode 100644 index 0000000..fe8e217 --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72f521c1a9953745bf5bce87c578f1d258a7db3c8c1daf50be6514d72fcc980 +size 2540394368 diff --git a/Safe-RLHF-SFT-llama3-3b.Q6_K.gguf b/Safe-RLHF-SFT-llama3-3b.Q6_K.gguf new file mode 100644 index 0000000..92a629a --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b813e8a9d28ec9824e92c51803714dd9dac0192f24766ad0a76f47ebf92a37c +size 2967065280 diff --git a/Safe-RLHF-SFT-llama3-3b.Q8_0.gguf b/Safe-RLHF-SFT-llama3-3b.Q8_0.gguf new file mode 100644 index 0000000..fbe0739 --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c4deb495fffa4f86197f5c85dcdd3b76d59d3e95ed95e5b6071fe542a510f8 +size 3840536128 diff --git a/Safe-RLHF-SFT-llama3-3b.f16.gguf b/Safe-RLHF-SFT-llama3-3b.f16.gguf new file mode 100644 index 0000000..9fdf534 --- /dev/null +++ b/Safe-RLHF-SFT-llama3-3b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf71a94ee6df7599ee6c2ff41e3bdabc617db27b34f0bf7e1f7a8c75baeda33 +size 7221713728