commit 0cdcd966ff831c20f7fa59d8ba46c47ce602a733 Author: ModelHub XC Date: Sat Aug 1 19:05:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RedSage-Qwen3-8B-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..85bb58f --- /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 +RedSage-Qwen3-8B-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RedSage-Qwen3-8B-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f05107b --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: RISys-Lab/RedSage-Qwen3-8B-Base +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- cybersecurity +- continual-pretraining +- targeted-pretraining +- text-generation +- casual-lm +- risys-lab +--- +## About + + + + + + + + + +static quants of https://huggingface.co/RISys-Lab/RedSage-Qwen3-8B-Base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RedSage-Qwen3-8B-Base-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-i1-GGUF +## 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/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RedSage-Qwen3-8B-Base-GGUF/resolve/main/RedSage-Qwen3-8B-Base.f16.gguf) | f16 | 16.5 | 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/RedSage-Qwen3-8B-Base.IQ4_XS.gguf b/RedSage-Qwen3-8B-Base.IQ4_XS.gguf new file mode 100644 index 0000000..ed3d146 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf84c7260636281d9d930ae057668aec58252f3d2beeb931d3bb90fc77589cc +size 4593292992 diff --git a/RedSage-Qwen3-8B-Base.Q2_K.gguf b/RedSage-Qwen3-8B-Base.Q2_K.gguf new file mode 100644 index 0000000..39fae60 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd85f2c07a727948a1360bc933daea7ee751c279f59a0f301bb9fbea627514d1 +size 3281729216 diff --git a/RedSage-Qwen3-8B-Base.Q3_K_L.gguf b/RedSage-Qwen3-8B-Base.Q3_K_L.gguf new file mode 100644 index 0000000..d3403b3 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aba2953044281d8ee917f3cf6ac41d7e7b9c7d458eddb31fd5dfdf004938a854 +size 4431390400 diff --git a/RedSage-Qwen3-8B-Base.Q3_K_M.gguf b/RedSage-Qwen3-8B-Base.Q3_K_M.gguf new file mode 100644 index 0000000..202a189 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fb8bcf3fdc26f7c2e9a6a91458ea9361b0f3453045817b285e29e76526ae1c +size 4124157632 diff --git a/RedSage-Qwen3-8B-Base.Q3_K_S.gguf b/RedSage-Qwen3-8B-Base.Q3_K_S.gguf new file mode 100644 index 0000000..2569b9d --- /dev/null +++ b/RedSage-Qwen3-8B-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585d0888204a04ba44ebe3bbc250b6a439625a31f81cebe7b174a024927575d9 +size 3769607872 diff --git a/RedSage-Qwen3-8B-Base.Q4_K_M.gguf b/RedSage-Qwen3-8B-Base.Q4_K_M.gguf new file mode 100644 index 0000000..b64b378 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5358d39b54d45870d57de3377d914073f94a45c920a4f33c3c5d09c76b66c957 +size 5027780288 diff --git a/RedSage-Qwen3-8B-Base.Q4_K_S.gguf b/RedSage-Qwen3-8B-Base.Q4_K_S.gguf new file mode 100644 index 0000000..c0b3379 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a638573d4993da6ec3247016fb776e177228fed66e7dc9300ec49dd1bc6272e9 +size 4802008768 diff --git a/RedSage-Qwen3-8B-Base.Q5_K_M.gguf b/RedSage-Qwen3-8B-Base.Q5_K_M.gguf new file mode 100644 index 0000000..f9be6e4 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f858aefed15005fb32f2c4201e1a873a551e060d11e4c9d4ca02c6540d56346f +size 5851109056 diff --git a/RedSage-Qwen3-8B-Base.Q5_K_S.gguf b/RedSage-Qwen3-8B-Base.Q5_K_S.gguf new file mode 100644 index 0000000..2d827e8 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454a95357f82cab177b1c254f47867fb687d343e30687c93de1c73816b781de7 +size 5720757952 diff --git a/RedSage-Qwen3-8B-Base.Q6_K.gguf b/RedSage-Qwen3-8B-Base.Q6_K.gguf new file mode 100644 index 0000000..1f47f50 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d582ec1d1552443274cac20707ae983b124b479d8083213dfed62c2bfde423 +size 6725895872 diff --git a/RedSage-Qwen3-8B-Base.Q8_0.gguf b/RedSage-Qwen3-8B-Base.Q8_0.gguf new file mode 100644 index 0000000..9586f02 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:851b7e66be2d2bc321f4d871bd5e330172aad3d1c58dc96975fd5b9eaad85171 +size 8709514944 diff --git a/RedSage-Qwen3-8B-Base.f16.gguf b/RedSage-Qwen3-8B-Base.f16.gguf new file mode 100644 index 0000000..acb8b11 --- /dev/null +++ b/RedSage-Qwen3-8B-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d595f06483440dd849b69b85aa82a91647d1a4f2b0d7cf8c2292c946eca5360 +size 16388040384