commit 084902390f0e47c81169f5a6a659a6bea142f58b Author: ModelHub XC Date: Wed Apr 29 05:35:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..39ba5cf --- /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 +Meta-Llama-3-8B-Instruct-DeepRefusal.f16.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-DeepRefusal.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.IQ4_XS.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.IQ4_XS.gguf new file mode 100644 index 0000000..a6095e1 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:331d5d8d8f3d52b18467a4001485ac8a662771f179c6e8dd06c2b2dbafa744be +size 4484363328 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.Q2_K.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q2_K.gguf new file mode 100644 index 0000000..ca1dc2f --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99745aa50ea212d63f349749615fd0f258d892e68da7885829572f6b1d25e881 +size 3179131968 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_L.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_L.gguf new file mode 100644 index 0000000..43565f0 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc354ab792eb71b2ca77c8fc2311ff75ee0b0b0b970563b34d2ddf309b4328b +size 4321956928 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_M.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_M.gguf new file mode 100644 index 0000000..62cab4b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d97c7d8de0af7713b2e0d612c055deba240862a19d1f7a09c435d6a2ad330b1 +size 4018918464 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_S.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_S.gguf new file mode 100644 index 0000000..31c6b77 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8ff1954de3a880312e9ec38578dcd927e497e716253432a41a8727e9a9f682 +size 3664499776 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.Q4_K_M.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q4_K_M.gguf new file mode 100644 index 0000000..861239c --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89bbe74e18c99927b351aca960566e571373d797d1047e7544e23cb0e244af25 +size 4920734784 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.Q4_K_S.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q4_K_S.gguf new file mode 100644 index 0000000..ee2afb2 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:699b690869dd82f21b214f2b4ecc5aeec798336830584556a0e04b5beeec8546 +size 4692669504 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.Q5_K_M.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q5_K_M.gguf new file mode 100644 index 0000000..0728d6c --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de07097afbeb5d800bb5866a84d74b24a7720e80f467bcab0f9080384cde3c8 +size 5732987968 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.Q5_K_S.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q5_K_S.gguf new file mode 100644 index 0000000..cfe723b --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8be729d7dfecd98f5d138c74c276062594c7fa0750ede6348da000ba02dfabd +size 5599294528 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.Q6_K.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q6_K.gguf new file mode 100644 index 0000000..1ae2726 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94255422e9f3eb7d69983f2813eccc28cfaf0db6341ea1bd28402b29f7bd547e +size 6596006976 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.Q8_0.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q8_0.gguf new file mode 100644 index 0000000..f7ad54d --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b94a08e3fd9f1be9a14854028dcf1cdb680c1a1b62fd2015c2c0c5013c2dfbf3 +size 8540771392 diff --git a/Meta-Llama-3-8B-Instruct-DeepRefusal.f16.gguf b/Meta-Llama-3-8B-Instruct-DeepRefusal.f16.gguf new file mode 100644 index 0000000..1cecca5 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-DeepRefusal.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5081bef6c2ac7c46f02d14d6d85d3c25b6f25891919cbe566946ef0ea59f77 +size 16068891712 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d95d207 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: skysys00/Meta-Llama-3-8B-Instruct-DeepRefusal +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- SafetyAlignment +--- +## About + + + + + + + + + +static quants of https://huggingface.co/skysys00/Meta-Llama-3-8B-Instruct-DeepRefusal + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Meta-Llama-3-8B-Instruct-DeepRefusal-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/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-DeepRefusal-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-DeepRefusal.f16.gguf) | f16 | 16.2 | 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. + +